Nearly a year ago, I wrote my first blog post for the Memo, discussing the massive potential of Mem X's AI features for creative writers. After noticing several people mentioning on Twitter that they were using Mem to write novels or non-fiction books, I decided that it was time to revisit the topic -- this time, featuring voices from the Mem community.

Recently I spoke to Adam Bloom, who previously served as an attorney and now works in marketing for a cryptocurrency exchange. On the side, Adam does some writing: he used to run a small production company with a friend, for which he wrote film scripts and TV pilots. Now, he's working on a novel about the crypto space, a new genre for him. "My big concern in approaching the project", he told me, "was that it was going to be a lot to get my arms around - that it was going to be very hard to keep track of all [my] ideas and keep them organized". As AI, and AI-assisted writing tools have been picking up steam over the course of the last year, he's been reading about how different pieces of software incorporating AI functionality are being used by writers, and this is how he came across Mem.

I also spoke to Mike Martin, a long-time user of Mem who "spent most of [his] career as an IT and management business consultant". Recently, he decided to switch focus and move into business and executive coaching, and decided to take all his learnings from the industry and write a book to "help other business owners and leaders [so that they won't have to] learn lessons the hard way".

Both of them are working on very different material in very different ways, but here I'm going to break down the most important components of their creative processes, and how they use Mem to supplement and amplify their writing work.

Getting your notes in

For Mem to be an effective tool for long-form writing, it's important to be able to get all of your notes in as easily as possible. Mike says that "even today, I find it to be the most frictionless tool for managing knowledge". For Adam, he needs to know that all the information he needs is stored within -- and accessible from -- his account. "That's the thing I'm depending on", he told me. "I am pouring ideas into this thing. I am dumping ideas into [Mem] as fast as I can think of them. And I need to know that when the time comes, I will be able to find them. To me, that's the value prop of Mem; having as many of my ideas at my fingertips as possible".

With our newly overhauled Imports process, getting information into Mem is easier and more reliable than ever. You can check out the update on the Memo here for more.

Organization within Mem

"What I really look to Mem for primarily is organization", Adam told me. He describes his Mem account as "really just the universe of the novel. It's not connected to my email, it's not connected to my calendar. It's a bubble. And all of the individuals who are tagged as people in Mem are characters from the book."

To keep track of his work, Adam makes sure to tag every character, every act, and every piece of research in the notes he takes. "I always tag any character that's mentioned so that if I look for all the notes about the character, it will come up. I use five acts [to structure my novel], so when I have a note and I'm thinking, this will be good for Act One, I'll just tag it as "Act One" and add it to that collection. And then I have some research documents, background for the novel, that I'll keep in my research collection. And then sometimes I'll just think of a line of dialogue or a little back-and-forth between characters. I'll just jot it down, tag the characters and put in a collection called "Dialogue" because that's kind of the best you can do. I think the problem is that when you try to over-organize stuff, you lose it [by making it too hard to find again]. And so the challenge is always that I want it to be organized, but I want it not to be too organized."

He continued: "I think the thing that people don't appreciate about doing this kind of [creative] writing -- and it's something that I had to learn as a writer, too -- is that the ideas are not going to come to you in order. It's sort of like watching a Polaroid develop. You're going to have an idea for the ending, and then you're going to have an idea for the beginning, and then you're going to have something that you might or might not use that happens somewhere around three-quarters of the way through. So, random pieces come to you at different times. And once you think you have enough, then you have to start figuring out how to stitch them together. And so it is a task of, like: I need to be able to see as much of it as I can at once. So if you over-organize it, you're hiding stuff from yourself. But if it's not organized at all, then you don't know where to look for anything. So the search is really important. The categories are really important. Character tagging, I find, is really important because if worst comes to worst, I know I mentioned this character in this note. [If Mem can] just show me all the notes about this character then I will find it. But the thing that I use to backstop all of it is the AI. If all else fails, I'm hoping that the AI will help me bring the right thing to my attention at the right time."

Mike relies less on the AI, and more on inline tagging to keep track of his work. "I've organized my work with references so much, I'm relying on that." He has one mem that contains links to all of the chapters of his book, which he writes within Mem, and their status - 'finished', 'needs revising', 'needs expanding'. "That's my primary way of organizing my workspace - I have this table of contents that I can jump around from and see the status of each chapter from... like a wiki-style page with hyperlinks".

He also finds that he's getting value out of the AI suggestions for which mems to add to Collections - for instance, a suggestion to add a mem with notes from a meeting he had recently, related to business coaching, to a Collection related to the book he's working on.

Mem tip:

Finding a way to keep track of how each of your characters develops across the course of a novel is another useful means of organizing the material for your narrative. This can be especially useful in a story with many different characters and subplots. What events are they experiencing, and what are they learning from them? How are you going to get them from Point A to Point B? (How did George Eliot write Middlemarch without the help of AI? We may never know!)

One way to chart this in Mem is with the use of our People feature. When you sync your email account with Mem, People will populate with all of your contacts from the last six months. But you can also create "People" in this view at will, by selecting the person icon in the top right, giving them a name, and then selecting the Create button. Say you have five characters whose development you want to chart: Alice, Bob, Chris, David, and Emma. Create People pages for each of them, and any mems you've tagged them in will appear in streamlined, chronological order in their People view.

Similar mems

The guiding principle of 20th-century surrealist art was a line from the French poet Lautréamont: "as beautiful as the chance encounter of a sewing machine and an umbrella on an operating table". That is to say, it's often when familiar but unexpected-in-combination objects are juxtaposed against each other that artistic inspiration strikes. As I discussed in my previous post on creative writing with Mem X on this blog, Similar mems can often bring about this kind of stimulating synergy between different notes, allowing you to look at the same material with fresh eyes, or reviving old notes with a new relevance.

The most exciting moment Adam had with Mem X's AI recently involved Similar mems. "You know, in the very early stages of the creative process, you're just having random ideas. What if this guy and this girl went to this place? What then?" He'd jotted a very short note down about a potential scenario that could emerge, then forgotten about it. Recently, while working on a more developed version of the story, he saw the note surfaced in his Similar mems. "I read it and I thought, huh, I have no recollection of thinking this. I have no recollection of writing this. And from this scenario, this could happen, and then this, and then this, and then this. Because by the time the note 'came back', my development of the novel was further along, so I knew more of where the story was going. So I was able to take that idea and tie it into three or four other ideas that I had already come up with, and what had been just a tossed-off, one-line note turned into an important piece of connective tissue for the entire story."

Smart Write and Edit

‍Adam told me, "Obviously, I want to write the book, so I'm not going to be like, hey, Mem, write chapter one. But what I have done is prompted it to write me a research report on the history of railroads in southeastern Iowa. Or a report about drug gangs in the Midwestern United States. And then the thing that I've learned to do, which works pretty well, is [prompt it to] write me the report and cite its sources, including links. So that means I can make sure it's accurate, and also that, if there's anything I want to follow up on, I can go to the sources and find more material to expand my understanding there if I need to".

I asked Adam why he felt using Mem was preferable to using Google for these kinds of questions. He told me it was largely a matter of being able to ask multiple questions at once, and then having all the information synthesized on his behalf by the AI. "Sometimes I'll have an idea, and I just need to find out if it's true or not. Do people even do these kinds of things? I'll just go to Mem and say, can you just look this up for me? Tell me, are there Mexican drug gangs in the Midwest? Where do they operate? How do they function, where do they get the drugs from? Are they coming from Mexico? Are they getting them from elsewhere? So for that sort of thing I use the AI as a research assistant. What I want is not to get stuck for half an hour when I could be writing. I just want an overview that I can double-check or dig into more later".

But he does also use Smart Write & Edit for some stylistic and tonal suggestions. "One thing I did once that was interesting was, I had written a speech one of the characters gives, and I was reading it over and I thought, this is good, but this guy sounds like he's from the East Coast, not the Midwest. So I put the text into Mem and [with Smart Edit] told it, make this sound more like this character's from the Midwest. It made a couple of small tweaks, and I didn't use all of them, but I did use some. I think it changed the word "mill" to "factory", or vice versa. And I thought, oh, that's a good point, I'll make that change."

When he's further along in the draft, Adam plans to "pass [the novel] through the AI just to edit it. Not to say you'll take all the edits, but it's interesting to get the perspective. What does it notice? And sometimes it might take notice of or change something where you think, that's a good point: maybe I should move this, or cut this, or whatever."

Mike says that while he doesn't use some of the other Mem X features so much, his experience with Smart Write & Edit has been "great". He told me that while ideating for his book title, he wrote several examples, and then asked Smart Write to add more. "I think this is where [one of the titles I'm considering] came from. These [suggestions] are really good, actually".

Mike also uses Smart Write within chapters to "keep writing for [him]", which he uses as a "jumping-off point" for rewriting, and for giving him ideas of where to go next when he's stuck. "I don't want it just to be an AI-filled book, but where I've found [some of the] most use is if I'm writing and I hit friction, and I'm not sure where to take it - then I would go to the AI and ask it to give me ideas". As a long-standing Mem user with many, many notes in his account, he's impressed, too, with how well Smart Write can mimic his voice and style. "That, to me, is the difference over something like ChatGPT -- I've got so much content in here that I did feel like it was continuing my voice [in the] AI text inside of [Mem]".

*

Two things particularly interested me when it comes to Adam and Mike's usage of Mem for their writing. First - as I said at the beginning of this post - is how different their methods of organization are: while Adam relies primarily on Mem X's AI features and search to arrange his material, Mike prefers to impose more structure through inline tagging and Collections. Each finds these two different means of organization possible within Mem works for them. Second is the ways in which they use Smart Write and Edit. Neither tend to ask the AI to simply write for them, but instead use it to spark inspiration, or aggregate information and verify hunches. Which makes sense - writers tend to do what they do because they enjoy the process of writing, rather than wanting to hand it off to someone, or something, else. To me - and hopefully to those of you reading this! - this demonstrated the very different creative processes accommodated by Mem, and how Smart Write & Edit can still be a hugely valuable asset to those writers who want to use generative AI to assist their work, but not be used by it.

As a social media manager, you know how important it is to create fresh, engaging content on a regular basis. But that's not always easy, especially when you're juggling multiple platforms and campaigns. That's where Mem's Smart Write and Smart Edit come in. 

Smart Write & Edit leverages generative AI to automate the writing process. This new frontier in artificial intelligence has the potential to fundamentally reshape how we perform tasks, from the most mundane to the most creative. With Smart Write, you can easily generate better content, faster, and tailored to your specific needs, freeing up more time for other tasks. And with Smart Edit, you can quickly review and refine your content, ensuring that it's perfect before you hit publish.

Here we’ll break down a few specific ways that Smart Write & Edit can help you in your work, from speeding up admin to firing up creativity.

Write a TikTok 

Producing TikToks, even the shortest ones, can be pretty time-consuming, depending on the amount of video editing required. Smart Write can't help you with that part of the creative process, but it can help you cut down on the amount of time spent on coming up with original scenarios and writing scripts for your videos. 

Step 1: Generate an idea/scenario outline

Step 2: Use prompts like “Expand on this”, “Make this longer”, “Give more details”, or “Flesh out this scenario” to elicit more details for a particular idea. 

Step 3: Turn the scenario into a script.

From here, you can make further adjustments or additions via Edit; for instance, instructing Smart Edit to “Include camera angles”, or to “Make the dialogue sound more natural”, or to “Make it funnier”.

Brainstorm marketing angles for a product 

If you’re a social media manager, the chances are you’re also quite involved in discussions around your company’s brand and marketing strategy.

One of the jobs that might fall to you is figuring out how to promote a new product to your audience. You want to maintain a cohesive sense of brand identity, but sometimes a one-size-fits-all approach isn’t going to cut it. You might need to figure out ways -- for example -- to make the product appeal to different sectors of your audience, particularly if that audience cuts across a large number of demographics. 

You can get the ideas flowing with Smart Write & Edit. Here’s one way to do it:

Step 1: Ask Smart Write to generate an article on your new product, and what makes it unique or important.  

The prompt we used here was “Write an article describing 3 unique capabilities of Mem’s Smart Write feature”.

Step 2: As with the TikTok script example above, you can expand the text if necessary. 

Because the prompt above asked for three unique capabilities, we told Smart Write & Edit to expand the paragraph given into three paragraphs. 

Step 3: Make this appeal to different audiences.

Below, we use the instruction “Make this appeal to a creative writer”, but you could use any variation on this depending on the audience you want to target - for instance, “Make this appeal to a venture capitalist”, or “Make this appeal to a product manager”.

You can see how Smart Edit takes the generic description of Mem’s capabilities above and specifically connects it to the work that writers do. 

Generating and formatting posts for different platforms

Sometimes coming up with a good caption is hard - especially when you have a character limit, or need to adapt the voice for different social media platforms. What are the most important things to highlight? Which hashtags should you use? How can you maximize audience engagement? Smart Write & Edit have the goods to make this process a little less creatively draining. 

If you’re drawing a blank on where to start, try asking Smart Write to generate something for you. Maybe you have the spec for a new product that’s about to launch? Or a blog post to promote? Try pasting any relevant documentation into a mem and then asking Smart Write to generate a summary of the contents for you. 

Now that you’ve got a shorter piece of writing, you can use Smart Edit to rewrite the content for whatever platform you’re interested in posting on. As you can see in the image below, there are two preset Smart Edit commands for Twitter and LinkedIn specifically: “Turn this into a tweet thread” and “Rewrite this as a LinkedIn post”. 

Here’s the preset command “Turn this into a tweet thread” in action.

You can prompt Smart Edit to include Twitter hashtags if it doesn’t do it on the first time round, as shown below. 

You can use custom commands for other platforms, such as “Turn this into an Instagram caption”.

Message admin 

Message admin is probably another task you find yourself performing frequently, whether that’s responding to Instagram DMs or emails. And let’s face it - message admin can be almost as enervating as writing cover letters. 

If you’re struggling with how to respond to a customer’s question, try outsourcing the work to Smart Write. Simply paste the message into a mem, then ask Smart Write to “Write a response to this message”. Smart Write will use the company-specific information stored in your Mem account to produce a custom reply on your behalf. 

If the generated response includes links, ensure that they are all correct before sending the message out.

Custom email outreach

When you’re not responding to emails, you’re sending them: reaching out to potential clients for your product, or trying to build creative partnerships. But if you want to make a good impression, you can’t just copy-and-paste your way to a deal; you need to show that you’ve got a good awareness of this potential client’s business needs, for example, or that you’ve thought about why the partnership you’re pitching is a good creative fit. 

Make sure the research you’ve done into this particular company, brand, or individual is stored in your Mem. Then, for the best results, you’ll want to create a basic email template that could look something like this:

You can save this as a Template for future reuse, so that you only have to do this writing for the first email you send.

Then, give Smart Write an instruction such as the following example: “Tailor this email to Jane TikTok content creator Jane Doe, explaining why Mem would be useful for their work”.

Ask Smart Edit to add a subject line, and there you go – a personalized email in a matter of seconds. Remember, the more information you have about the people or brands you’re pitching to stored in your Mem account, the better Smart Write & Edit will be at customizing your email for them specifically!

It's technically still a jobseeker's market right now, but that doesn't make the process of finding and applying to jobs any less painful for applicants.

You can set yourself up for success by working smarter, not harder, with Mem. That means getting organized, sure -- with Mem, you can store all your notes, documents and research for quick and efficient access - but it also means using our AI-powered features to cut down time spent on repetitive or soul-draining tasks. After all, nobody in recorded history has ever enjoyed writing a cover letter...

‍Knowing what you want

‍Knowing what you want can be a difficult part of the job search, especially if you're just starting out. There are a few things you can do to help yourself get a better sense of what you're looking for in a job. Taking the time to reflect on your past experiences can be a great place to start. Consider the skills you've developed, the roles you've held, and the activities you've enjoyed most. You can also research different jobs and industries to gain a better understanding of the opportunities available to you. Finally, talking to people who are already in the field or role you're interested in can be a great way to gain insight into what the job entails.

Check out this post for Tim Klein's tips on using Mem for self-reflection and determining the types of jobs best suited to your interests and skillsets.

Searching for jobs

Once you know what kind of jobs you're interested in, it's time to feed Mem with as many resources as possible. This is going to help you keep track of new opportunities, deadlines, and so on, but it's also going to improve the quality of Mem's Smart Write & Edit suggestions - which is going to be important when you start writing your applications.

Here are a few tips:

• Connect your emails to Mem to ensure that any emails regarding job opportunities from listservs, newsletters, etc come straight through into your Mem account and you can search for them easily. To do this, head to Flows in the left-hand side bar, select the People & Email syncing tile, then follow the instructions there to connect your account.

• Use Mem Spotlight to quickly save job opportunities you see online without switching screens. Just press Command+Shift+Space on Mac to pull up the Mem Spotlight window, then hit Enter to save the webpage to a new mem, followed by Command+Enter to finish. You can also save a webpage to an existing mem, or highlight a piece of text and push that into a mem via Spotlight if you only want to save a specific piece of information.

• If you're also on the lookout for job opportunities via Twitter, make use of our Mem It for Twitter function to save tweets and threads directly to your Mem workspace. Select Flows from the left-hand side bar, then select Mem It for Twitter, and follow the steps outlined there to get your Mem and Twitter accounts connected. Once you've done that, all you have to do is reply to a tweet or thread with "mem it" and mention @memdotai to save it to your Mem account.

• Using Mem's Google calendar integration, you can keep track of job applications, deadlines, and other important information related to the job search process. This can help you stay organized and on top of deadlines, while also providing a way to easily review your progress and accomplishments. Connect your calendar by selecting Flows in the left-hand side bar, choosing Calendars, then following the instructions outlined there.

Subscribe now

Applying for jobs

Now that you've landed on the jobs you're interested in, it's time for the applications (and the dreaded cover letter). This is where Mem's Smart Write & Edit feature is going to come into its own, helping you to quickly build out job applications, resumes, cover letters, emails to employers, and more. Smart Write & Edit can generate entire documents from scratch, suggest content based on what you've already written and what you have saved in Mem, and help you edit and refine your work.

‍Resume

‍If you don't already have a resume, use Smart Write & Edit to help you draw up a good template with a prompt like "Write me a personalized resume template that will impress employers, including details on each section".

If you already have a resume, you can use Smart Edit to tailor it to the job you're applying for, by asking it to include keywords and phrases that match the job description.

You can also use some of the Mem suggested prompts to edit your resume: for instance, if it's too long (you should aim to keep your resume to a page if possible, or two pages max), then you can ask Smart Edit to "Summarize this and make it shorter". If you're struggling with how to describe your work experience in formal language, try using the Smart Edit prompt "Make this sound more professional".

Cover letter

Maybe you saw this recent Business Insider piece on using ChatGPT to write cover letters for two different jobs -- a purchase-ledger clerk and a social media assistant -- and asked the respective hiring managers what they thought. While the recruiter for the purchase-ledger clerk position said that they would probably follow up with the applicant for an interview, the recruiter for the social media assistant position felt that the cover letter lacked the requisite personality they'd be looking for in a suitable candidate for the role.

That makes sense - what ChatGPT lacks is the ability to truly personalize writing to you. And while you could give ChatGPT more information to work around that, your best option is to use Smart Write, which will automatically draw on your notes, knowledge, and unique written voice to produce a custom cover letter that stands out from the crowd. Use it to craft an attention-grabbing opening paragraph (highlight the text and instruct Smart Edit to "make this more engaging"), or help you come up with unique and compelling stories to illustrate your experience, skills, and qualifications.

Interview preparation

If you've impressed with your resume and cover letter, then the next challenge will be the interview (or, most likely, interviews) that follows. Preparing for this stage of the application process can be daunting - what if they hit you with a curveball question? - but you can make it easier on yourself by utilizing Smart Write & Edit.

For instance, you can use Smart Edit to summarize key points from your research and notes, so you can quickly review important information before your interview. If your interview is taking place over video call, you can also keep these notes open in the Mem app for easy access to help you answer questions in the interview itself.

You can also use Smart Write & Edit to generate potential questions you might be asked during an interview, and help you formulate thoughtful answers to them. Compile your research on the company and role you're applying for, along with your resume, in a single mem and then ask Smart Write to "Make a list of possible interview questions for [the specific role] at [the company you're interviewing with]".

Let us know how Mem is working for your job search by DMing us on Twitter or emailing stephanie@mem.ai!

Over Thanksgiving of this year, artist Michelle Huang’s tweet about using GPT-3 trained on her childhood diaries to speak with her younger self went viral. When a Mem It for Twitter user saved the thread to their account, I knew I had to talk to Huang about her project — and about sixty seconds into our call, we’d pretty much established that we are kindred spirits. Over the course of the next hour, we talked creativity and cynicism, self-narration, and, as Huang put it, the potential of AI for “wonder”.

Note: this interview has been condensed and edited for clarity.

SP: Hi Michelle! When did you first become interested in doing inner child work, and when did you first have this idea of bringing that personal growth work together with generative AI?

MH: Let’s see — I think my first interaction with inner child work was probably five years ago or so. I think there is some part of me that was kind of unconsciously doing it [before that], in the sense that I would go through my diaries sometimes when I was back at home for the holidays and think, wow, there are some sparkly insights in here. I remember the kind of energy and belief that anything in the world could happen [at that age]. So I think some part of me was still trying to capture and preserve that feeling as I went on through my adult years.

Then, I remember after GPT-3 came out, I was with my tech-obsessed friends and we were like, hey, let’s read the GPT-3 research paper together. That provoked so many interesting ideas for me. And then when I went back to my parents’ house during the holidays — this was December 2020 — I started thinking about the diaries again. And I actually tweeted about this in December 2020 — “what if I trained GPT-3 on my inner child?” Because the entire internet was talking about GPT-3 at that time.

So I actually started transcribing my journals then, looking toward doing this project, but I didn’t finish it because I was distracted with a lot of different things, and that was when I quit my job, moved to Asia, started to make art full-time. And it was only this year that I was back at my parents’ place, cleaning my room, and I saw my stack of journals and thought, oh, that project. That’s when I started transcribing again and actually finished it.

SP: What ages did you keep your diaries between?

MH: I started around probably like age 7, and then kept them pretty consistently.

SP: Oh wow, young!

MH: Yeah, super young. I think my earliest diary entries were — well, I remember having a whole journal dedicated to what I would do in RuneScape, which is this online game. It was funny; I would detail what I did each day in RuneScape. Killed five chickens, that kind of stuff. I don’t know if you played RuneScape?

SP: I didn’t, but I also kept diaries when I was younger — for nowhere near as long as you, but pretty consistently between the ages of 11 and 15. And I’ve also been revisiting them over the past few years, thinking about doing something with them. But the entries are so jarring in juxtaposition: I’ve got an entry in March 2003, describing the invasion of Iraq. And then you turn a few pages and you’ve got an exhaustive ten-page recap of the series finale of Buffy.

MH: That’s so funny. Yeah, I have that juxtaposition too, entries about Runescape followed by, “I went to a piano concert last night” or “I just had a fight with my sister”. But yeah, I just remember the transition between when I was playing RuneScape, and writing a lot about that, and then “graduating” from RuneScape, but I was still writing my diary, and it was like, “OK, I guess I can document my real life instead of my virtual life now”. So it was an interesting transition point. Anyway, yes — started when I was 7, and wrote in it every day, every other day, until I was 18, and went to college.

SP: So what was your selection process in terms of the material you trained GPT-3 on? I imagine manageability dictated at least some it, if you had over a decade’s worth of diaries.

MH: Absolutely. I had actually just finished transcribing one stack of diaries, completely verbatim, and then I looked over at another, larger stack and I thought, if I do all of these like this, this isn’t going to be done in 2022. It’ll be a 2025 project. And in some ways, that could have been cool, because I’m sure there will be better AI tools then. But I wanted to just put this out there because I felt like I’d been learning a lot and wanted to share that.

“I feel like this whole project made me realize AI that can serve as a mirror, by engaging with and seeing [new] parts of ourselves” (click to tweet)

Aside from practicality, I thought having some mundanity in the entries I chose was important to capture the experience of life, which is full of moments where we’re moving and growing and adapting, but also full of moments of stasis.

But I think a lot of what I wanted to understand about my inner child was less about, oh, I talked to my crush five times today — moments and feelings which are still important and valid — and more about what her values were, what perspectives she had on the world: was it something she wanted to lean into, or was it something she was scared of? If she was scared, why? Why did she feel like she wanted to keep leaning in and trusting in it? So I tried to choose entries that recorded experiences where I had a very clear articulation of a worldview.

SP: And how would you characterize yourself as a child?

Honestly, I think that there are parts of me that are still very much the same, and there are parts of me that are very much different. I think that it’s funny because sometimes I’ll still talk to my elementary school friends and they’ll say, Yeah, you’re the same person, and I’m like, Yeah, I guess so.

I actually did this experiment where I got back in touch with my old kindergarten teacher during the pandemic. I got my yearbook photo and I was trying to get back in touch with all of my classmates and my teacher, and I reached out to her and I got her email and we caught up over Zoom, and it was incredible.

Anyway, I think [my childhood self] was very optimistic about the world and how people could work and live together. I feel like in my childhood, I probably had to grow up early, but I still feel like there is a part of myself that maintained the optimism that things would work out. And I think there is a period of time where it’s like the midwit meme. Are you familiar with the midwit meme? So, it’s this bell curve with a guy who doesn’t think very much, then someone who has average intelligence but thinks it’s superior, and then the guy who’s kind of transcended everything and is very intelligent and actually thinks in the same way as the guy who doesn’t think very much. So for me, I think I started off being optimistic, thinking everything was going to be great. Then I went through a period of jadedness where I would overthink things. It’d be like, ‘reality isn’t the way everyone says’, ‘my dreams are crushed’, etc. And then I feel like after connecting back to my inner child, it’s like: actually, I understand the reality of things, but it’s still important to be hopeful. If you have something to look forward to, life just get’s infinitely better. So I think I’ve kind of returned to that now.

SP: Yeah, I feel you on that. I had this point last year where I’d experienced a couple of betrayals, and I felt really for a while like I couldn’t do anything right. You know, it really disillusioned me, and I closed myself down a little bit. And then it was only this year that I was able to get over that, and kind of open up fully again, to trust, to even be a little bit naïve. At the end of the day, I’d rather be naïve than cynical.

MH: Good on you, for being brave and continuing to open and show the openness of your heart to others. You know at least for me, there’s a part of my experience where I was thinking, oh, well, I was so naïve before, and now I know more. And if I go back to [trusting like I did in] the past, am I regressing? Or will I be hurt again? And everyone talks about childlike trust, and it’s easy to trust when you’ve never been hurt, but being able to open your heart again is way harder than having your heart open in the first place.

As kids, too, we’re just delighted by being alive. We’re still getting used to experiencing things, and almost every day we encounter something new. And then as we grow up, we kind of take being alive for granted until something crazy happens to us, and that’s when we stop and need to think, Wait, actually, life is great.

SP: And that’s interesting what you say about your childhood friends saying you’re essentially the same person you are now as you were then. I’ve had similar experiences with school friends — you know, I think of myself as wildly different to how I was when I was at school, and so I should be different — you should change and grow. But it’s funny, because sometimes I’ve spoken about how much I feel like I’ve changed as I’ve got older, and my oldest friends will say, no, you were always this, or that, or whatever quality I’ve told myself I only grew up to possess.

MH: Yeah, it’s pretty wild when you ask: what parts of ourselves do we not see, or maybe even not want to see? And then the parts of ourselves are reflected like a mirror with friends, who can see some parts of ourselves maybe even more clearly than we can. But maybe some aspect of our personality is a huge mystery to them, yet we’re very clear on its importance to ourselves.

SP: So this may be a little redundant off the back of that conversation, but I heard someone say once that you’re always the same person inside that you were when you were 14. Do you agree with that?

MH: I do think essence is something that stays constant. And of course, let’s say people go if someone goes through significant trauma, they may behaviorally act different, but I think a lot of their world view or what they hope to believe or what they actually believe remains intact. I think a lot of times the most difficult part about trauma is trying to reconcile your internal conception of yourself, or of the world, versus anything that has happened to make you reevaluate that.

I think that even though I used a range of diaries written between the age of 7 and 18, most of them were actually from before I was 14. At that age, I was starting to get jaded, and reading over them I felt like I wasn’t accessing my inner child any more — more, my inner angsty adolescent self. So most of the entries I used in this project are from when I was between 10 and 14. That’s when I was, you know, sentient enough to have thoughts, post-RuneScape era, but not jaded.

Honestly though, I’m surprised how much has stayed the same. And even through the journey of midwitting and becoming jaded, I’ve just eventually returned back to this place because I feel more free in doing so. And I feel much more aligned to it. So, I think I’m pretty much my 14-year-old self still. I peaked in middle school.

SP: I think you’re peaking now. Do you feel like you’re easily influenced by other people’s opinions of you?

MH: I would say it feels contextual. I’ve been noticing that now I’m in Japan, which is more of a collectivist- and more of a society-oriented culture, that I’m actually being more influenced and more vulnerable in general. I didn’t expect being in a different culture to have such an impact on me. So it’s interesting to think about how my behavior, my affect, my boundaries shift based on whether or not I perceive that I am in a high-trust society.

For example, in Japan, people can walk past a garage sale that’s completely unmanned, with a bunch of artifacts outside, and then there’ll be a cup that has a label that says, “Everything’s ¥100”. So you grab whatever you want and then just put ¥100 in, and then you can walk away. But if you had something like that in New York, where I used to live, things would just disappear. Someone would probably take the cup with the coins in, too. And I think about how I was in New York: I really had boundaries where I would say to myself, no, I’m not being influenced by someone unless they’re a person I really trust. While in Japan, I’m actually much more likely to mirror someone, even in the ways that they interact. If I ask someone, hey, how am I supposed to do this thing? and they give me advice, I’ll genuinely respect and listen to what they say. Which is to say, it varies depending on context, and I think that’s OK. I can have a hybrid of boundaries depending on the place I’m in, geographically.

SP: I know you wrote in your thread about the uncanniness, the trippiness of talking to your childhood self. Could you speak a little bit more to that experience?

I really went in without any expectations. I thought, you know what, I have no idea whether or not this AI chatbot will be a representation of these values and interests that I fed in or if it’ll just conjure up someone that I don’t really relate to. But it occurred to me that the whole project felt less about accuracy and more so about engaging tangibly with a part of myself, instead of constructing a mental model: would she say X, Y, or Z in response to this question? And the visual representation I got back felt like back in the good old days on AIM, when I’d sit at the computer, hunched over in the dark typing to my friends, and somewhere, they’d receive that message, type a response, and that response would magically pop up on my screen. It really did feel magical in the sense that it felt like I was typing on my computer and my younger self was at another computer, typing back, wherever she was in the world.

The whole project felt less about accuracy and more about engaging tangibly with a part of myself, instead of constructing a mental model (click to tweet)

Really, it felt like the computer was a time portal. It was the closest thing I’ve ever done to time travel in my life — so far. And besides that, what was really uncanny was getting responses from my “younger self” that I felt were representative of what my inner child would say.

So I’d ask her things like, what are your favorite memories? And she would respond with things that I had actually put in the diary. Even more uncanny — I asked her what her favorite color was, and she said blue. Now, that was my favorite color when I was younger, but nowhere in the diary do I outright state that. But somehow, [GPT-3] inferred that I liked that color.

Then I asked her, what are some of the world’s issues that are bothering you? And she said, mental health advocacy. And you know, that’s an area that I’ve only really become dedicated to within the last two or three years, but it was never a conscious effort to move into that kind of work. But maybe the AI picked up on things in my diary entries where I’m talking about my mental health, my friends’ mental health, how I want to support them and uplift them. And that’s pretty wild. I feel like this whole project made me realize AI that can also serve as a mirror, in the same way that we talked about friends doing, by engaging with and seeing [to us obscure] parts of ourselves that maybe have always been lucid to them. Wanting to do something in mental health advocacy. When it came out with that, I thought, wow, I don’t remember seeing that coming as a kid. AI certainly did. And maybe if I’d had a tool like this at my disposal when I was 15 and had fed this information into AI, it could have told me from the get-go: this is the thing you want to do. Maybe I would have just done it straight away. But then again, I think it’s important to appreciate the journey and to be able to converge on a path naturally, rather than just pursuing the most efficient route to something. I’m very much a journey-over-goal kind of person.

SP: Me too. And you mentioning the power of AI to sift out these things — I spoke to someone recently who’s using Mem and AI for these self-growth journaling projects at Boston College. And we were talking about how it feels like psychoanalysis, really, that the AI can pick up on and surface these submerged ideas and beliefs and patterns that you don’t necessarily recognize consciously.

So I’m interested, given what you’ve said about your interest in mental health advocacy, what do you feel about the potential for AI in that space — psychoanalytically, or therapeutically?

MH: Yeah, I think there’s a lot of potential. And I think so far we’ve seen a lot of cases of AI being used in destructive senses, or in productivity-only senses: like, let’s do this thing faster so we can ultimately replace humans, et cetera. And this [generative AI for creativity] feels like a vote for AI towards wonder, and for mental health, and for us to embrace and be able to see our own humanity more, just reflected a little bit differently. So I feel really excited about that. But so far as any technology goes, I feel like it’s very much agnostic and it becomes an amplifier to whatever direction that we set it in.

Generative AI feels like a vote for AI towards wonder… for us to embrace and be able to see our own humanity more, just reflected a bit differently. (click to tweet)

I definitely see how people could use AI to replace human therapists, and I don’t think that’s the right way to go. I think it should be a supplement. I think that the human connection is really important. There are parts of humanity we just don’t really have a scientific backing for but that weknow are there. And I think it’s important to also respect that. So I think for me, while AI can enhance or reflect back our humanity in different ways that maybe we weren’t able to see without it, it can’t capture everything. So I think that it’ll be more of a supplement than a replacement.

SP: Apart from the inner child work you do, what activities make you feel closest to yourself as you were or remember yourself being as a child?

Both art and writing. My journal entries were very much me being in this world with myself and being able to express anything that I wanted. And I had really vivid dreams, so I’d write about my dreams, and write stories based on them, all of that sort of thing. Overall, in my practice now, the whole meta aspect of being able to create a world out there that mirrors something that exists in here is something I’m able to engage with with that same curiosity and joy I had as a kid.

SP: Yeah, let’s talk more about your art. What was your path to becoming an artist full-time?

MH: I started off in premed in college, very much going down the doctor route. I was and still am fascinated about scientific discovery. But in America, the infrastructure of the healthcare system is not the best. So I thought, I should learn more about systems, and instead of leaping into medicine, get a more holistic understanding of how all these things operate together. So I ended up going into business, then finance for a little bit. That was… [laughs] — well, I thought, “alright, cool. I understand this: time to get out”. Then I worked in product at a healthcare startup, which was fun, but not creatively satisfying. And it was shortly after leaving that that I decided to commit to being an artist. So I’ve been an artist for the last two, three years and casually for much longer. I do a lot of things at the intersection of art and technology, in various permutations. It really spans a wide range of things. But ultimately I’d say they’re all linked as experiments in human flourishing.

SP: Was your creativity something you felt encouraged to explore as a child?

MH: Well, I have very traditional Asian parents, and they had that Asian immigrant work ethic. Like, “we didn’t come to America for nothing. You’ve got to be successful”. So even to this day, they’ll be like, oh man, if you’d just stayed on the premed path… Because they’re worried about me, and I know it comes from a place of love. But it’s like, why work for fifty years until I retire and then feel financially secure enough to become and artist rather than just doing it now?

And that was a pressure at first, money-wise, because when I was living in America, I was living in New York and San Francisco, very expensive cities. So I ended up moving out of San Francisco and moving to Taiwan to increase my runway. I mean, a month of rent in San Francisco can be six months’ worth of rent in some parts of Asia. My plan was to go out to Asia, make my money last longer, and spend a lot of time doing art and figure out whether or not it was actually for me. So I did a lot of different artistic experiments and posted them online, and got some traction from that, contract work and freelance work. All of these opportunities were inbound, rather than me reaching out to people. And that got me excited, because it seemed like people were really resonating with these ideas. That’s when I started thinking: can I push the envelope even further?

“If people are in nature, and they’re in a community of other creators, and they’re not paying for their living and have enough time to genuinely think about and figure out what they want to do, can we create a more optimistic and ideal society?” (click to tweet)

SP: Is that when you started to come up with the idea for your current project in Japan?

MH: Yeah, exactly. So the idea behind this project [AkiyaDAO, a planned series of creative residencies in Japan] really came from moving to Asia, making my money go further, and pursuing art, a combination of all those things. I was thinking: why does it have to cost so much just to exist? And I wondered if I could help to create a community in which people don’t just feel trapped by a certain, unfulfilling kind of existence where they’re doing things they don’t enjoy just to pay the bills. Really, these houses will be experimental containers for human flourishing. If people are in nature, and they’re in a community of other creators, and they’re not paying for their living and have enough time to genuinely think about and figure out what they want to do, can we create a more optimistic and ideal society?

And I feel very thankful that I had the wherewithal to go to Asia and start building this creative container for myself in the first place. I know that’s not accessible to everyone, so being able to support other artists: I knew I had to do it.

SP: We’ve already touched on this a bit, but what do you think about the rise of generative AI in the last few years, and its impact on creative practices?

MH: Well, to go back to my creative pursuits as a kid, like I said, something that was really important to me was worldbuilding. You know, I wasn’t doing 3D rendering or anything, because what kid does that? Maybe Gen Z — I don’t know. But I was drawing a lot, trying to convey these worlds in my mind. The only problems was they kind of sucked. But now I’m doing digital art. Because it was like, OK, it’s going to take me 20 years of professional training to actually be able to depict these worlds that I dream of, or these concepts that I want to develop. I just can’t get there in a realistic timeframe with traditional tools. But now I can use motion graphic design and things like Midjourney, and that gets me way closer to the images and the ideas I really want to express. And I think it’s great to have these tools to help you evoke and inspire the same feelings in others that you have in yourself.

SP: Yeah, the motivation to convey something meaningful feels like an important thing to emphasize. Now that generative AI has really taken off, and everyone online is obsessed with it, we’re getting a lot of reductive, dichotomous discourse about machine creativity vs. human creativity. But the worry that writers will be replaced by AI — it just feels like an unnecessary concern. First of all, I think the more competent AI gets at writing, the less interesting that writing tends to be. But also because when people read a novel, they’re interested in what somebody meant when they wrote it. And we want to talk to authors about what they meant, or try to puzzle that out with other readers. And you can’t ask a machine what it intended to convey by writing a piece of fiction. Or you could, but you wouldn’t get a meaningful response. As readers, would we want to debate the meaning of a book we knew had been produced by a machine with no life experience?

MH: Exactly. I definitely see AI as more of an iterative partner in the sense that, hey, maybe I am thinking about this image that I have in my head, but I’m not that proficient at drawing things. How do I share this with others? And maybe I can type it into Midjourney. It might not be correct, but that image could allow me to have more ideas and allow me to feed and spark more things. It’s not a question of one thing or the other. I think of AI as a partner in crime that works both by being a soundboard, and by being scalable beyond all human capability and effort.

I’m optimistic about this. Given there’s so much AI that lends itself to art direction and the art world, it feels like people are able to lean into more of their creativity by using it.

SP: I hope so, too. Last thing — a comment, not a question, but I found that exchange in which you ask your younger self if love or freedom is more important, and she says “love, because freedom can be lonely”, very moving. It’s something I had actually been thinking about myself a lot, prior to reading your thread. 

MH: Yeah, I was surprised by that because, honestly, I was thinking about that as well. Because when I left New York, which was in mid November, I was seeing someone there, but I was going to Japan and working on this project. And then I was like, do I hold on to this person or do I want to have freedom? Or do I want them to have freedom? It was very much about asking questions that I was curious about my own answer to. So the AI was like, a spokesperson for myself in some way. And she was like, “Love”. And I thought, yeah, I resonate with that. I’ll take that answer.

Follow Michelle on Twitter here.

Follow AkiyaDAO on Twitter here and donate to the project here.

Subscribe now

We’re excited to announce that Mem X Smart Write & Edit are now being rolled out to waitlisted Mem X subscribers on the Mem web application (MacOS and Windows desktop app releases to follow soon). Work smarter, not harder, with your own knowledge-aware AI assistant that’s personalized to you.

What sets Smart Write & Edit apart

Smart Write and Smart Edit are unique among AI-powered writing assistants because they combine the radical capabilities of large language models with the personal knowledge stored in your Mem account. This means you can craft highly-personalized writing that draws on the specific contents, voice, and style of your knowledge base. Other large language model applications can produce high-quality written content, but none of them knows you in the way that Smart Write and Smart Edit do.

For instance, you can ask Smart Write & Edit to:

• Retrieve a coworker's contact details for you

• Give you action items from your last meeting with a particular company

• Recommend a new book for you

• Suggest on-brand ideas for your next blog post/article/product launch campaign

• Write a persuasive, customized email to a client highlighting the benefits of your company's new product

• Suggest relevant discussion points for your next meeting with a coworker.

No other AI-powered writing application has these capabilities. And the more of your own notes you take in or put into Mem, the more Smart Write and Smart Edit will learn from your own writing style and knowledge base, making it an even more powerful tool.

Using Smart Write

When working in a mem, hit forward slash (/) to bring up a dropdown menu. From the top of that, you can do three things:

1. Ask Smart Write to add a title to the paragraph or piece of writing you are working on.

2. Ask Smart Write to add a summary of the existing contents of your mem.

3. Give Smart Write a custom instruction on what to write for you.

Like Mem itself, there are countless ways you can use a Smart Write custom prompt; the only limit is your imagination. You can ask it to:

• Write from something from scratch

• Come up with a recipe that uses the leftover ingredients in your fridge and pantry

• Generate a viral Twitter thread

• Create a detailed report summarizing the findings of a recent market analysis

• Write a press release announcing the launch of your company's latest innovation

• Generate a set of frequently asked questions and answers for your company's website

• Write a cold outreach email to a potential new hire, explaining why you think your company would be a good fit for them.

Using Smart Edit

To use Smart Edit, highlight the piece of text within your mem that you wish to edit. From the black toolbar, select the magic wand icon. In the pop-up input field, tell Smart Edit how you want it to change the highlighted text.

Smart Edit works on both a stylistic and formal level. For example, you can ask it to:

• Change the style of a particular piece of writing (e.g., "Make this funnier", "Make this more colloquial", "Make this more poetic")

• Change the angle of a particular piece of writing (e.g. "Make this appeal to a person under the age of 25", "Make this more skeptical", "Make this more enthusiastic")

• Turn bullet points into prose

• Take a book or dissertation chapter and turn it into a conference paper or lecture that will take a certain amount of time to read, or matches a particular conference's theme

• Pull out soundbites from an interview transcript.

The Age of Symbiotic Intelligence

Artificial intelligence already facilitates our day-to-day lives. Every time you use your smart phone, listen to a recommended song on Spotify, or let Gmail finish a sentence for you, you are engaging in a relationship with artificial intelligence. But, like any relationship, it requires reciprocity in order to be tenable. We do not really tell the algorithms that shape the content we see on social media platforms what we are interested in; they tell us. Algorithms decide how we see the world, and offer us only content that reinforces that view. We know humans are much more interesting, multifaceted, and complex than that, which is why Mem X Smart Write & Edit use artificial intelligence not to circumscribe human behavior and activity, but to irradiate, enrich, and augment it. Our mission is to help humans create more and think better by reducing time spent on menial activities (tedious admin, searching for difficult-to-find information), meaning that our users can concentrate their energy on doing the things that machines can't.

We envision a future marked by accelerated creativity, increased efficiency, and seamless cross-contextual knowledge transfer - a future in which you can query Mem as you would a personal assistant, using natural-language searches to bring together and synthesize knowledge across channels - from Slack DMs, to emails, to Calendar meetings, and more. Soon, requests like "Summarize my last 5 meetings with Acme Corp", "Write this email in the voice of my coworker", and "Plan a trip itinerary for me using my flight confirmation emails" will all be possible.

How to sign up

Subscribe to Mem X here and join the waitlist here to unlock Smart Write & Edit as we roll it out. You’ll start out with 50 free Smart Action credits included in your Mem X subscription. To purchase additional credits, click your profile icon in the top right corner, click Settings, and navigate to “Smart Action Credits” under “Mem X.”

Share your most mind-blowing Smart Write & Edit use cases on Twitter and tag @memdotai — those who share the best use cases will win Smart Action credits and a special prize.

Subscribe now

Welcome to the first in a new, ongoing series of short interviews with people who've found cool ways to use Mem in their everyday lives. After we published this piece in September — a collection of excerpts from four interviews with Mem users — we realized that we should make showcasing interesting use-cases an ongoing project. We hope you find them as inspiring as we do. Read on, and sign up for emails to be notified when we post our next instalment.

“I did a stint in Obsidian and Roam and then Notion, but I don’t want my notes to be their own aesthetic project. So when I saw what you guys were doing, and the simplicity and low-friction of it, that seemed really attractive”, James Hull told me. James works as a wine importer on the East Coast, and is hoping to turn his Mem into both a collaborative workspace and shared knowledge wiki for him and his team. “We’re only a small company, it’s four of us, so it definitely has the potential to be a system we can use, and have [Mem] as a little company data center”.

James explained what that knowledge database might look like in more detail for him and his company. “For us, we’ll have something like a page with the information on a wine producer, but then you can start branching off from there. For instance, what’s the history of the grape variety they’re using? What’s the history of the area they’re working in? There are all these avenues that open out from there.”

Now that they’re working with more winemakers, having a shared bank of easily-retrievable information is more important than ever. “We work with 35 winemakers right now, and sometimes you’ll be on an appointment or something like that and think, oh God, what was the soil type they use again? Or what vine-training method do they use? And being able to access that really quickly is great. And then over time, we’ll be able to flesh out their profiles in Mem even more, and get really concise, solid information built up that any of us in the company can access and alter and refine.”

Right now, James has a fairly consistent professional routine with Mem, jumping in on Mondays to plan out what his week will roughly look like and taking note of any appointments he has or needs to make. (In the future he’s hoping to use Mem recreationally, too, for storing the music he plays and journaling).

But being a wine importer isn’t a typical office job where you’re at your desk from 9 to 5, so the ability to get “tasting notes, information, little nuggets” into Mem while on the go is crucial for James. “‘Cause sometimes, if we’re in Italy or something, we’re visiting with a producer and we’re standing in the middle of a field-”

“You’re not going to get out your laptop”, I guess.

“Yeah, exactly”.

And while James is pretty decent at “bumbling [his] way through” Italian, he’s not fluent in the language, so quick-capture is even more important when he’s overseas talking to producers and trying to keep up with the conversation. “Oftentimes when we’re visiting, my boss [and the producer] will be speaking in Italian to each other, and then my boss will repeat in English what they just said. It all happens conversationally, and I need to get down all the information we’ll need to sell the wine later”. He’s considered audio-recording these conversations for extra ease, but right now being able to capture notes in Mem on the fly works for him.

Texting a wine’s tasting notes to Mem is also something he does a lot. “Often on Mondays the team will taste some wine together. So I’ll taste it, take notes, use the text [function]”. Sharing the mems with the rest of the team is useful, too, especially “if only one or two of us can be at the tasting”: that way, everyone can be on the same page about a particular wine’s flavor profile. James has a template set up for wine tastings, so he can add that to a new mem and record all his notes there.

I’m interested in the language used to describe wine for a couple of reasons: one, because the taste of a particular thing is, philosophically speaking, a quale — a subjective, first-order experience; and two (relatedly), because the terms used to describe wine are generally analogous or metaphorical. On his Substack Let Them Eat Cake, former restaurateur T. W. Lim recalls how he once asked a wine retailer how he selected the wines he sold in his store. The retailer replied: “sometimes, when I taste a wine, I hear a bell. If I hear a bell, I’ll think about selling that wine.”

Lim goes on:

“Sometimes, when I taste a wine, I hear a bell” is still the most essential and consistent rubric I know for engaging with wine, because unlike every professional course of wine training I know of, it embraces the ineffability of what happens every time we taste.

I ask James about the particular inadequacy of language to describe the taste — the “ineffability” — of a wine, and if that’s a problem he and his team ever come up against when sharing tasting notes. Maybe it’s easy to agree on the levels of tannin and acidity, or the fruit aromatics of a wine, but what about “angular”, “ethereal” or “brooding” as wine descriptors?

James agrees that the language of wine can be pretty subjective, but he’s interested in seeing how Mem’s AI learns to deal with that, especially as NLP models across the board continue to improve and refine over time. “I think you’re leaning on an important question, [and that’s] whether as my notes build up and the AI gets better, how much it can connect to this insular language that we wine people have”.

Sign up for Mem now at get.mem.ai.

College might be the first taste of freedom for many of us, but it also comes with packed schedules, greater responsibility, and tight deadlines. Finding a balance between schoolwork, extracurriculars, and socializing can require a lot of concentrated effort.

Personal planning has enjoyed something of a vogue among under-25s on TikTok in the last couple of years, with people sharing their morning/evening routines and organizational hacks with their followers. Time management has become, as Wall Street Journal reported in August, a "visual art form" online.

But aesthetics, of course, aren't the only thing to consider when choosing a knowledge management/personal planning tool that works for you. Last fall, The Verge published an article discussing how the hierarchical model of information storage and structure that seems intuitive to most people aged, say, 30 and over, feels pretty foreign to most current undergraduate students. Rather than thinking of the data stored on their computers in terms of "filing cabinets" and "director[ies]", they conceive of it rather as being like (per one Princeton undergrad) a "laundry basket where you have everything kind of together, and you're just kind of pulling out what you need at any given time". For people who grew up with search engines at their disposal, thinking about how to hierarchize the information they generate and store doesn't come naturally.

The good news is that Mem works according to this mental model, too. We enable information retrievability not through complicated folder structures but through our powerful AI, which surfaces relevant information when you need it, and cutting-edge natural-language search capabilities that mean you can talk to Mem -- "what was that concept I learned about in Bio last week?" -- like you would a person.

Here’s a runthrough of how you can use Mem to organize your college life, from note-taking to revision, all without having to think in terms of complicated, artificial folder structures:

In lectures

You probably already take your lecture notes on your laptop or iPad, rather than in a notebook; you can get information down faster, it's searchable later, and, if you're a messy writer like me, you don't have to worry about whether you'll actually be able to read them later.

Taking notes in Mem is just as easy. At the beginning of the lecture, open up a new mem, tag it with the semester and course name/number (e.g #FALL2019 ENG 217: Introduction to Science Fiction), then start typing. Next lecture, make sure to use the same tag and you'll be able to build up a virtual "notebook" for the course - like you can see below.

‍

If you receive a physical handout in lecture, you can quickly snap a photo of it, then go to your mem and hit / and select Add an image to add the photo to your notes, keeping all your material for the course together.

You might even want to add links at the top/bottom of each mem to the previous/following lecture's notes, for added ease of navigability. You can create links by typing + followed by the name of the mem you want to link to, as shown below.

‍

‍

Richard Berry, an MBA student in Australia, has this routine: “Every Tuesday night we have a lecture. So I go into class, and I’m taking notes. I take notes in one mem and kind of arrange everything by topic. So whatever the topic is, I’ll introduce a headline, and then start writing notes below. Then as soon as the topic changes, I’ll just create another headline and take notes there. After the lecture, I’ll go through and clean things up, and then split everything up into topics and link the mems”. This helps him think, remember and make connections between information less in terms of lecture structures and more in terms of related ideas.

For recurring notes that follow a similar or the same format (like lecture notes or class notes), you can also save time and make sure you capture all relevant information by creating notes templates.

Alice, who’s studying for a PhD in the UK, remembers taking notes for her Master's degree in "one Google doc that had around 50 pages". In Mem, however, she uses custom templates to ensure she records all the important data and metadata from her reading. “I’ve got a section for the title, author, the journal or book it’s in [if it’s an article], its year of publication. And then I have task boxes to mark whether I’ve annotated it, whether I’ve finished it, whether I’ve added it to my Google sheet where I list everything I’ve read. And then I have sections for core arguments, key critiques, and quotations. The most useful section is probably at the bottom, which is important references or dialogues. And then these link to mems, like these little stub pages, that I’ve created for each scholar. Obviously on the page itself there’s no information, but on the sidebar I can use the “Mentioned by” section to create this web of connections - like, OK, this scholar is mentioned in this paper, and also in these papers”.

To create a template, head to Flows in the left-hand side bar, select the Templates tile, then click the blue Create template button on the top right of the screen. For instance, your lecture notes template might contain sections like "date", "lecture title", "key points", "resources" (any handouts, recommended articles or websites), and "questions" (anything you're still not clear on that you want to follow up on later).

Managing your course notes

Keep all the material for each of your courses together (syllabus, notes, readings, assignments, etc) by tagging your mems with the relevant semester and course name/number. You can view all your mems by tag by clicking Tags in the left-hand side bar and selecting from the drop-down menu (click All Tags -> if the tag you're looking for isn't shown in this view). To add a more fine-grained level of organization, you can also tag your notes by topic (e.g., "Picasso", "Cubism", "Guernica").

If you've been supplementing your course reading with academic articles and want to include those in your notes, you can do that simply by typing /, then selecting Attach a file.

Of course, you don't just want to have your knowledge siloed within each course you take. A huge part of learning, at the college level and beyond, involves synthesizing knowledge from different sources, making cross-disciplinary connections that strengthen and expand your ideas of certain concepts.

For instance, a literary class on narrative theory might help you to think about how legal texts in your law class are constructed, or a biology class on adaptation could give you a different perspective on how technology evolves.

Similar mems makes it easier to draw these parallels because the AI that powers it can determine conceptual as well as textual relationships between mems. If you take all your course notes consistently in Mem, you’ll find that Similar mems will get smarter and smarter at figuring out these relationships, and it will become easy to find the links between your courses that will help you to build up a total synthetic knowledge field.

Similar mems are only available in Mem X, the paid, AI-powered version of Mem, but we offer a 40% discount on Mem X subscriptions to current students!

Working on projects with classmates

If you've been given a group project or assignment, Mem is an easy and effective way to collaborate with others.

Create a group in Mem by selecting Groups in the left-hand sidebar and then clicking the blue Create group button in the top right of the screen.

A pop-up will prompt you to choose a name for your group -- e.g., “BIO 302 Week 4 Group Assignment" -- and once you've done that, you can hit the white Create group button.

Right now, you're the only member of the group, so add people by clicking on either the grey Add member button beneath the list of current members, or the blue Add member button, again in the top right of the screen. A pop-up will then appear asking for the name of the person you want to add to your group.

If you've worked with your classmates in Mem before, start typing their name and then select it from the dropdown. If not, no problem - just type in their email address and select Invite [email address], and then hit the Add to groupbutton to send an invitation to your Mem group via email. Repeat until all members have been added to the group.

Now you and your group can collaborate in real time on your assignment. Use the Comment function to leave notes for the other people in your group.

Anyone you invite to your Mem group will be able to view and edit the mems you share, whether or not they have a Mem account, so you don't need to worry about getting all your classmates to sign up for and download the app before you can start working together.

Writing term papers and reports

Taking notes in Mem throughout the semester is going to make your life so much easier when you come to writing a term paper or report. I've written before about the assistive power of Similar mems when it comes to creative writing, saying that you can "[t]hink of it as Wikipedia link-surfing, but for your own brain. Similar mems can help you make unexpected connections between ideas, see things you haven’t explicitly thought of before. This isn’t just a question of knowledge management, but knowledge generation."

That's just as true for schoolwork as it is for fiction-writing. As soon as you start typing, Mem's AI can work its magic, suggesting notes that connect to the topic you're writing about. For essay subjects, this means you’ll never be stuck for what to say next.

While Mem only offers export in JSON and markdown format right now, anything you write in a mem will copy and paste cleanly to Word, Pages, Gmail and so on without any formatting issues. No need to worry about having to spend ages fixing weird line breaks in order to submit your paper!

Schedule and deadline management

Sync your Google calendar with Mem to show all upcoming events in a banner at the top of your timeline -- all you need to do is head to Flows, select the Calendar tile, click the Connect a Google Calendar button, and follow the steps from there.

If you're a daily to-do list kind of person, you might want to set up a Daily mem in which you can plan out your workflow for the day. You can customize your daily mem to appear at a specific time and on specific days of the week, and structure its template in a way that makes sense for you. It could look something like this:

‍

To set up a daily mem, just go to Flows, followed by the Daily mem tile, and choose what days and time you want your daily mem to appear on your timeline, along with the text/structure you want it to contain. Then hit the white Save Daily mem button at the bottom right of the screen.

Studying for exams

When it comes to exam preparation, everyone has different techniques that they swear by. You might find that you want to do most of your preparation “offline”, on paper; studies have shown that handwriting notes tends to lock them into your memory more firmly than typing them does. But Mem can still be an important aid in your review process.

One idea we like is recording the audio of lectures on your phone and attaching those files to your notes. When it comes time to review the material, you can play these recordings back and make another set of notes based on them, and compare them with your original notes.

You can also use Mem’s task function/view to create and keep track of your study checklist. From within a mem, just press [ (left square bracket) followed by ] (right square bracket) and then hit Space to create a checkbox.

You can create separate checklists for each course you’re taking and check off topics as you go, as shown below.

You can track all outstanding tasks by selecting the Tasks view in the left-hand sidebar. Hit the little dropdown on the top right of your task list to view Open tasks, Open and completed tasks, or Open, completed and hidden tasks. Below you can see all the open tasks remaining for the ENG 205 checklist from the above example.

Want to snooze a task for later? Select it in the task list, then click Send to → on the right-hand side of the task list, and type a time and date in the input field. The task will disappear from your task view until the time and date chosen. You can also hide tasks by selecting them in the task list and clicking Hide → on the left.  

Alace, a student in India, told us that she often creates mems that work like flashcards: “It’s a good way of testing yourself; you just put a question at the top, leave a few gaps, and then write down the answer, and then you can quiz yourself pretty easily”.

Aesthetics

And, finally, a note on our interface. We prioritize clean design above all, so that there’s no barrier to getting your thoughts down on the “page” as quickly as possible. That doesn’t mean we don’t care about aesthetics - it just means that we want our aesthetics to tie into our functionality. Rather than building an app in which you can lose hours customizing different templates and layouts – and then find that you’ve done none of the work you needed to – we’ve built one that looks slick and doesn’t distract you from the task at hand.

Sound good? Try Mem for free today at https://get.mem.ai.

The history of knowledge work has been one of constant evolution. From the early days of the industrial revolution in the late 18th century, when knowledge work was largely confined to a few specialized fields, to the rise of the information age in the mid 20th, when knowledge work became a defining feature of the modern economy, we've undergone dramatic changes in our relationship with information.

Along the way, we've acquired new capabilities that have propelled the human experience. From factories that enabled the mass-production of consumer goods, to the internet that created a shared global consciousness.

Today, we sit at the precipice of yet a new era — one where machines can not only automate (factories), and accelerate (internet), but even think and reason. It's hard to imagine that the new capabilities we will gain in this era will be anything short of revolutionary.

We're excited to announce that we have raised $23.5M of Series A funding, led by the OpenAI Startup Fund, to accelerate our efforts towards augmenting humans with the capabilities of this era. And yes, we are hiring.

At Mem, our mission is to leverage machines that can think to build products that inspire humans to create more, think better, and organize less.

For a researcher, it means being able to consult, and utilize, existing bodies of literature at a scale and speed that was previously unimaginable.

For an investor, it means being able to make better decisions by analyzing vast quantities of data in a fraction of the time it currently takes.

For a screenwriter, it means being able to finally put writers-block to rest, and create generational narratives that capture our collective imaginations.

The list goes on.

At its core, all of knowledge work revolves around a set of common activities. We seek out information and inspiration, we synthesize it, and then store it away. Over time, we draw on the knowledge we've accumulated in order to generate new insights and ideas. Then, the cycle repeats.

An investor may read 10-Ks, a screenwriter screenplays, and a researcher papers on arXiv, but the fundamental unit of work is similar — each activity is a slight variation on the cycle above.

By marrying machines that can think with domain specific knowledge, we can create a personalized knowledge assistant for every knowledge worker. That is the essence of what we do.

To that end, we have two further announcements to make today.

The first is that Mem X is now officially out of beta. So if you were on the waitlist, congratulations, you're in! And if you weren't on the waitlist, don't worry: you can sign up now and join the party.

The second is the announcement of two new capabilities of Mem X that leverage generative AI in a transformative way. We are calling these features Smart Write and Smart Edit.

Like Mem itself, there are countless ways to use Smart Write and Edit — the limit is simply your creativity. You can ask it to:

• Produce a piece of writing from scratch (e.g., "Write an article explaining why sans serif fonts are so popular with DTC brands")

• Summarize jargon-heavy research papers to be more digestible

• Come up with counterarguments/rebuttals to something you have written

• Write a recipe that uses the leftover ingredients in your fridge and pantry

• And so much more...

You can sign up for the Smart Write waitlist here.

--

Until recently, the field of artificial intelligence that most preoccupied our collective cultural imagination has been that of robotics. Science fiction writers dreamed up various scenarios of human-robot conflict; ethical debates raged about the implications of creating machines that could potentially surpass human intelligence in many areas, or the risks associated with imbuing robots with the ability to make decisions on our behalf. We've been conditioned to fear the imminent overtaking of humanity by our robot overlords.

But science fiction is exactly that — fiction. And if the past year has been any indicator, we think the future will be a lot more inspiring than it is dystopian.

We are entering a new era of personal computing — the symbiotic intelligence era. Machines will not replace us, they will simply make us better. They always have, and we are in the business of making sure they continue to do so. If you're interested in joining us on this mission, take a look at our careers page here.

DALL-E 2 prompt: “ A person lying on a couch in a futuristic-looking office with a psychoanalyst sat in a chair nearby taking notes, neon, digital art”

In January of this year, the writer Sheila Heti started a limited-run newsletter for the New York Times, made up of extracts from her personal diaries. Heti has been journaling for more than a decade, and amassed more than 500,000 words that document the events of her life, and her reactions to them. In the series for the NYT, Heti imported all of her diary entries into Excel and arranged each sentence in alphabetical order, in the hopes that it would "help [her] identify patterns and repetitions" across her life. "With the sentences untethered from narrative", she writes, "I started to see the self in a new way: as something quite solid, anchored by shockingly few characteristic preoccupations".

I was thinking about Heti's project as I spoke to Tim Klein, a teacher at Boston College and author, with Belle Liang, of How to Navigate Your Life, about how he has been using Mem to develop a curated journaling space that he hopes will help students to articulate their interests and values, and identify recurring patterns in their lives across time.

Klein, who also consults with high schools, colleges, and other organizations across the world, works in the science of purpose -- which he says "at a high level is like living a life that's personally meaningful, uses your strengths, and contributes to the world". If you've attached purpose to what you're doing in life then "all the research would show" you're probably more self-directed, have better relationships with your peers, are more engaged, and have a better mental buffer against the effects of stress. That's the thing, Klein says: stress can often be a motivating energy to achieve goals if you can see how those goals accord with your own sense of purpose in life. But "when you hit adversity, you're like, why am I doing this? And if you don't have a meaningful answer to that, then that leads to [a sense of] meaninglessness, which can [manifest as] depression, anxiety, all of those things", he tells me.

A sense of purpose is also a decision-making tool: a compass that can help keep you on track and aligned with your values when making important life choices. The challenge, of course, is knowing what is personally meaningful to you - the contribution you want to make to the world, and how to spot opportunities to make those contributions. So Klein wants to both encourage people - young people, especially - to reflect more on their lives ("the more you think about your life, the more likely you are to find purpose in it, right?"), and to put more institutional systems in place to encourage that self-reflection. "Right now", Klein explains, "we have a college and career navigation crisis on our hands, where more people are going to college, more people are in work, but no-one is successfully navigating school, work, vocation, and life". That's because "we've never taught people how to decide what to do with their lives. We tellthem what to do - get your grades, all of that stuff. But we've never taught them how to decide".

Klein thinks giving specific language to what "a sense of purpose" might look like to an individual is crucial. Without breaking down and analyzing why something feels meaningful to you, it's often hard to think about how you can pursue careers and hobbies that will provide you with that sense of meaningfulness. He and his research partner Belle Liang have isolated four elements of purpose, which are as follows:

• Using strengths that feel like a core part of your identity, to be able to show up as your best self for whatever you're doing

• Having the opportunity to refine and gain new skills that you are motivated to learn and master

• Making decisions that align with your core values

• Meeting needs in the world that you personally care about.

"So essentially purpose becomes using my strength and skills to make a positive impact that aligns with my core values. Again, the challenge is you have to know what your strengths are. You have to know the skills you want touse, you have to know the values, you have to know the impact. So our work is around equipping people with the language of strengths, skills, values, and impact, to help them identify those core elements and then when they think about doing something in the future, they can go, OK, is this an opportunity for me to use my strengths? Is there an opportunity to gain skills I care about? Does it align with my values? Can I meet a need in the world?"

To equip them with that language, Klein starts with four of what he calls "compass" questions, that reveal a person's basic values, talents, and drives and naturally lead to the elements of purpose discussed above.

"So, how do you want to be remembered?" he asks me.

My answer: ideally, as someone who was loving, and as someone whose writing made an impact on people.

"OK, so heart and mind", nods Klein. "And how do you want to grow as a person?"

I tell him that I'm always trying to get better at setting boundaries, and not absorbing so much of my identity in other people.

The next question is trickier: what do I want to stand for, and what am I willing to sacrifice in doing so? We discuss the binary of growth versus stability, and I decide that I probably value change and new experiences more than security, even when that change involves difficulty. (As a friend once wrote to me, “I know you have an ambivalent relationship with comfort”).

Finally, Klein asks, what impact do I want to make? What problems do I want to solve? Here, I suppose my answer is similar to that of the first question.

I’m no stranger to psychoanalyzing myself, but there’s something very helpful about thinking in terms of these questions, and verbalizing my answers to them. As Klein and I are talking, I’m already thinking about how illuminating this kind of introspection could be when combined with Mem’s AI. If you journaled in Mem consistently using Klein’s language of purpose, would our AI be able to - in essence - surface things from the subconscious over time, by identifying latent patterns in your writings about your behavior and values?

As it turns out, that’s exactly what Klein is hoping for. He shows me a Daily mem he has customized to include not only a schedule section and to-do list, but also five questions that encourage introspection, including: what would make today feel purposeful? what impact do I want to make? Each question links to another mem that provides a vocabulary and definitions for answering these questions.

“So”, Klein tells me, “they might have all this stuff to do, but here we're trying to provide them with a vocabulary for capturing what feels meaningful to them. One week it might be self-direction, the next it might be self-care; it might be recognition, or social ambition, or whatever. And then the idea is that they use this vocabulary to journal in here and the vision would be that they're using this language over time to talk about it, and that vocabulary becomes a framework for Mem’s algorithm”.

He’s hoping that as students journal in Mem each day and accrue more and more entries that verbalize their values, it might help them be more intentional when, say, applying for a job. “Imagine you’re looking at the values of this organization [you’re thinking about applying to], and they say, we prioritize integrity and discipline. Then the idea is, you’d be able to go to your Mem, search for “integrity”, and see every single time you’ve talked about that value, how you’ve applied it and where, and then you have this whole information set you can use to help you decide on whether this organization is a good fit for you”.

Klein also has another template that he wants to use for this project that is for capturing "moments that matter". “So if you experience a little formative moment during the day then you can capture who was involved, what happened, where, that sort of thing. But then we're asking you to think - what exactly was important about this? How did the moment make you feel? What strengths did you use here? What skills did you leverage? We're asking you questions based around those elements of purpose to get you to figure out what exactly made this moment meaningful, you know?"

What Klein also hopes his project will encourage students to do is "connect the dots between disparate experiences" in their lives. Being able to "tell the narrative of why we're doing what we're doing" is really important for a sense of coherence and meaning in our lives, he tells me. That tracks with me: I'm quite a nostalgic person, but I generally find it a source of strength and stability, because it helps me connect my current sense of identity with all the past "versions" of myself. Being able to see how past experiences have shaped the person I am now helps me perceive more meaning in my life, rather than considering the me of the past as a stranger whose actions I cannot comprehend. (So, more of a “continuer” than a “divider”, to borrow the terminology of Joshua Rothman’s recent New Yorker article).

In higher education, though, learning management systems like Canvas or Blackboard make it difficult for students to synthesize knowledge across classes, or record insights that they can take forward with them. “You take a class, you do this reflection, you write all these papers and all of that information lives in the class itself. It doesn’t stay with you as a person as you advance in life”. By asking his students to capture and collect all their learnings and experiences in one folderless digital space, Klein is hopeful that they’ll be better equipped to find coherence across their lives. “The easier it is to make a coherent jump between one thing you’re doing and then the next, the more purposeful your work’s going to feel; the harder it is, the more you’re going to question everything, you know?”

In the future, Klein “would love to take people through workshops where we go through the importance of these elements of purpose, help people to articulate these things. And then we set them up in a custom Mem workspace prepopulated with all the vocabulary and definitions and so on, and get them journaling in there.”

The last big problem Klein hopes Mem can solve is the “Blockbuster video”-style decision-making process in higher education. “If you go on a website, it’s all categorized in alphabetical order. But now we live in a Netflix world. I’ve always had this idea - and Mem is the closest thing to it - of [a digital space] where students can identify the values they care about, the skills they want to be learning, the impact they want to be having, and over time that turns into an algorithm that recommends classes, majors, extracurricular activities that other people with the same purposes have found meaningful”. Kind of like collaborative filtering but for identifying meaningful pursuits. The reason they can’t do it right now, Klein tells me, is because the psychometric inputs simply don’t exist yet; they don’t have enough data to curate this experience. But the more people use his Mem journaling space, and use it consistently, the closer this gets to feasibility.

“You’re always more unreal to yourself than other people are”, Marguerite Duras once said - meaning that the sense of a solid, consistent identity is only a function of external observation.  But maybe less so in the world of enhanced introspection that Klein envisions.

“Venture capitalist”: sounds pretty exciting; what does it actually involve?

Well… kind of. Venture capitalists are investors who provide funding to companies looking to expand or to startups that are trying to get off the ground. From the initial pitch through to vetting, funding, and checking in on how the company is using their investment, VCs are involved every step of the way.

Below I’m going to walk through a typical day in the life of a venture capitalist, and show how you can integrate Mem into you and your team’s workflow to save time, maximize communication, and create a knowledge database that facilitates easy capture, retrieval, and proactive surfacing of information.

In the morning

As a VC, it’s likely that one of the first things you’ll do in the morning is check news outlets – both general and trade – for any relevant updates in your market.

If you see something interesting, you might want to share it with your team for discussion. Use Mem Spotlight (Cmd + Shift + Space on Mac) to quickly capture the article without context-shifting, adding any tags you like and tagging your collaborative Mem workspace to share it with everyone.

You and your team can then add comments and reply to each other using Mem’s Comment function.

If you see a new company that sounds interesting and you want to contact them, you can do a quick search in Mem to see if any of your team have reached out to them already.

If not, add a quick task to your Daily mem to remind yourself to contact them during business hours. You can set up your Daily mem by going to Flows, and then selecting the Daily mem tile. Choose what time you want your mem to appear each day, then customize the template in whatever ways you want. Using a Daily mem consistently is a great way to set your agenda for the day, as well as reminding yourself of any outstanding or ongoing tasks from the day before.

Throughout the day

Most of a VC’s day is spent in meetings and phone calls: listening to company pitches, doing due diligence on potential investments, and following up on investment leads. Mem’s Google Calendar integration lets you see what meetings you have coming up; you can also join them from within the app by hovering over the event and selecting Join call.

Taking effective and easily-retrievable notes is crucial when you’re meeting with people back-to-back. You can do that in Mem simply by hovering over the meeting in the calendar strip at the top of the home page and selecting Create mem for event. This will open a new mem that populates with the Google Calendar event name and a list of all the meeting attendees.

To reduce your time spent on repetitive tasks and to make sure you capture all the important information from a meeting, you can create notes Templates for meetings you participate in frequently. For instance, in pitch meetings, you’ll want to include details like the name of the company, the name of its founder(s), and other key pieces of information to refer back to later. You can do this by heading to Flows, clicking Templates, and then clicking Create new template on the top right of the screen. Customize your template and name it, then hit Create template at the bottom of the screen.

Now, you can access that template from any mem just by typing forward slash (/) followed by the name of the template, and then hitting Enter.

From your meeting mem, you can also create links to new mems to capture supplementary information in more detail without cluttering the mem you’re currently working in.

For instance, when writing down the name of the company who’s pitching to you, type +, followed by the name of the company, and then hit Enter to create a link to a new mem. Click the link, and the new mem will open in the right-hand side bar. Here, you can jot down the most important facts about the company, and supplement the information with your own research after the meeting.

*

Another typical facet of a VC’s daily work is performing due diligence on companies they’re thinking of investing in, to check that they are who they say they are.

One way to keep track of this process is by creating a mem for your due diligence work and adding tasks to it by typing [ ]. When you complete a task, you can check it off the list and see what you need to do next. Add links to notes from each of these investigations so you can find them all from one location.

You can also see all of your outstanding tasks by selecting Tasks in the left-hand side bar.

Writing up due diligence reports is also easy from within Mem. Related mems in the right-hand side bar displays any mems that share the same tags or contain similar phrases to the one you’re currently working on. This means that all of your relevant notes will be surfaced when it’s time to start compiling your report, making the process of pulling and combining the information you need both quick and painless.

*

Twitter is also a major source of news and information, and you’ll probably find yourself checking it throughout the day. If you see a tweet or thread you want to revisit later, but don’t have time to read properly in the moment, you can use Mem It for Twitter to import it into your Mem account so that you can easily come back to it later. To use Mem It for Twitter, head to Flows, select the Mem It for Twitter tile, then follow the steps to connect and verify your Twitter account.

Once you’ve done this, the next time you see a tweet or series of tweets you want to capture, reply to the post with “@memdotai mem it”. This will send the tweet straight to your Mem account, as well as generating a public link to the mem as a reply. You can also add tags to your tweet so that the thread is automatically associated with a particular topic within Mem: e.g., “@memdotai mem it #investing #newcompany”.

What sets Mem it for Twitter apart from other tweet-saving products is that it also uses AI to generate a summary of the thread you save. Like I’ve written elsewhere, this allows you to take on new information quickly, and see how that information fits into your existing knowledge of a subject, making it easier to retain. If you’re a busy person with a packed schedule, it’s a crucial tool for staying on top of important, fast-moving things like industry news and trends.

In the evening

VCs typically spend a few evenings each week attending business dinners, pitch competitions, or other networking events. In these cases, capturing information – a company name to Google later; a fellow VC’s contact details – is as vital as it is during the workday – but it’s a little awkward if you whip out your laptop to take notes while you’re sharing a glass of wine with someone.

That’s why we’ve also developed Mem to be used on the go. Using Text to Mem, you can quickly send notes via SMS, Whatsapp, or Telegram straight to your Mem inbox. So, instead of writing something down in your Notes app – which you’ll promptly forget about later – you’ll be reminded of the conversations you had and the things you want to follow up on when you check your Mem inbox the next morning.

You can set up Text to Mem simply by heading to Flows, Texts, and then configuring your preferred texting platform.

*

Are you currently using Mem for your work? Or have suggestions for other kinds of Mem use-cases you’d like to see featured on the Memo? Drop me a line at stephanie@mem.ai with your ideas!

At Mem, we’re focused on making our product something that models reality. To do that, we have to think about humans as much as technology. Every time we release an update to Mem, we’ve thought carefully through its workflow and how it will help users on the other end of the product.

That might explain why so many of the users I’ve spoken to recently have highlighted Mem’s “simplicity”. Our goal is always to make your experience of storing, sharing, manipulating and generating knowledge in Mem as easy as possible. If we’re doing our job right, you shouldn’t be thinking of Mem as an aggregate of various features, but as something that enables a particular experience.

With those two things in mind, I thought it would be a good time to showcase some extracts from interviews I’ve conducted with Mem users. Each of these individuals – whom I spoke to over video chat, or by email – told me that the product was “simple”, in one way or another, but what exactly that simplicity meant was different to each of them.

We think it’s good to be reminded as often as possible of the people we’re building for, and their unique stories. I’ll let them take it from here.

‍Adrian Evans

“I like that Mem is going on its own path, in its own direction”, Adrian told me when we spoke in July. “It’s not copying other applications”. Adrian is a British horticulturalist, journalist, and landscape designer based in Finland; he started using Mem shortly after Christmas last year, and currently has around 1,000 mems in his account. “Having used it for a couple of days, I went through all the video tutorials on Youtube, and it just became an invaluable daily tool”.

Mem’s the first thing he opens daily, he told me. “I look at what I was doing the day before [on the timeline], then I look at the calendar strip at the top and I know what’s coming up for the day. I fill out my daily mem and think about what tasks I’m going to do today. Then I’ll make my day work around that”.

While Adrian also uses apps like Evernote, Craft, Obsidian and Notion to store information, he finds them lacking in terms of retrievability - “you have to know what’s in there to be able to find it”. The idea of an app that could use artificial intelligence to proactively surface relevant notes was one that he wanted to be “on board” with. “In something like Obsidian, you have to make your own connections. I want the AI to do that for me!”

Not needing to hierarchize or categorize information before entering it into Mem is also a big plus. “I can dump anything into Mem, whatever I'm looking at online, and through the AI technology it can find what’s useful later”, he said. “I like everything all in one place. Mem keeps it all there in the package”.

Currently, Adrian uses Mem in both his personal freelance work, and with a team of five others – all new to Mem – on a Research and Development project for a company that provides green solutions for urban environments. There have been “positive responses” from the team, he told me; “they find it easy to use. Before the company was using GSuite, and all the information was basically in filing systems. I wanted to use a tool that could surface appropriate information, because there’s so much talk of second brains these days”. Now, they don’t have to spend time thinking about where to store information once it has been created, nor which folder to go to in order to find information that already exists in the system.

“I like testing whether the AI can make connections”, Adrian said of using Mem for his own work. “I read Tiago Forte’s book [Building A Second Brain] and he said you will create notes that you will never look at again. But when I’m writing my columns, Mem can pull up all kinds of different thoughts, different sorts of information that I’ve put in the system”.

“Mem”, he concluded, “is just easy. It’s not complicated”. And that’s important for making the product appeal across a range of ages. “Young developers shouldn’t just be looking at a young target market. You have to think about how to onboard older people as well. I really appreciate the Slack group, it’s a really nice resource. In terms of customer service it’s great, and that gives more meaning to the app itself. I feel invested”.  

Jen Vanderveen

“My ideal world is one where I operate on one screen”, Jen, an elder law attorney told me. When her ADHD worsened a couple of years ago, she started to look for coping mechanisms – “carrying around note cards and scribbling [on them]”, as well as trialing some digital note-keeping applications. After reading about Mem on an ADHD blog, she decided to “jump in and give it a shot”. “Within two days” of joining, she said, “Command Shift Space bar [the Mem Spotlight shortcut for Mac] was my most-used keystroke, because you just think of something and hit that Tab, type it in … it’s natural to just hit my keys and type”.

The fact that it isn’t necessary to context-switch in order to store information in Mem is one of Jen’s favorite parts of the app. “That can be a big problem for people with ADHD”, she explained. But “[with Mem Spotlight], I don’t even have to stop what I’m doing and consciously switch screens”. And, with the ability to send texts directly to Mem, “even when I’m in the car, I can get those random ideas out of my head and into the app”.

Jen told me that the issue she’d found with other PKM systems was that they often allowed her to see too much information at once, which would distract her from her current task. In Mem, however, those distractions are minimized. “The nice thing about Mem is I get a clean screen… then I don’t get distracted by, ‘oh, wait a minute, I need to go back and -’. Nope, clean screen. Put your idea down, and move it aside”. She also likes the fact that there’s “not a set way you have to do things” in Mem. “With OneNote, which I used to live in, everything has to fit into a folder… [but then] you end up with one folder just full of garbage. And then you have to actually go in and move things to a folder and it’s a process and that’s a pressure point. That’s where things don’t get done”.

For Jen, everything goes into Mem, whether that’s her legal work or a reminder to tell her husband that pesto sounds good for dinner. Whenever she wants to run a calculation, she won’t “get a scratchpad out”; she’ll call up Mem Spotlight and use that instead. “That way people aren’t trying to read my chicken scratch somewhere down the line. I can just go back and print [that mem] to a PDF and shoot it off”. With everything in one place, she can run a search for anything she knows she’s been thinking about recently and find what she’s looking for. “When I’m in those situations where it’s like, ‘I know I was thinking something about powers of attorney recently, what was I thinking?’ I can go into Mem and run a search and pull it up.”

“This has been a life-changer”, she told me. “We’re finally at the point almost where my computer is listening to my brain and just doing things for me. Isn’t that what we all want, really?”

Mariano Hvozda

Mariano Hvozda, who works in hospitality and is an ADHD and autism coach, wrote to me via email: “What I like about Mem is that it is very lean and simple to use… The best apps are those that do what they do very well, [rather than] getting more complicated”.

Mariano has also been diagnosed with ADHD, and describes himself as a “very curious person”, but someone who also gets “overwhelm[ed]” by the “amount of information in today’s world”. For the last few years he’s been working on developing a personal knowledge system that is “easy” on his ADHD. He echoed Jen’s sentiments about Mem Spotlight – “it is very easy to… capture a quick thought, note, or action, without really having to shift tasks or workspace” – and highlighted the ability to be able to capture information on the go as important for him.

My thinking happens anywhere and having my [cell phone] handy to drop a fleeting note helps a lot. When you have a good idea, you want to record it somewhere, otherwise it is likely my ADHD will make me forget it, and you never know when your mind is going to strike gold!

Right now, he told me, he’s developing his usage of Mem. “Until now it has been a ‘brain dump’ of thoughts, ideas and reflections from my personal life. A few weeks ago I [started] to use a separate account for my work life: using it to capture 1:1 notes from meetings (my biggest struggle to remember)”. In both capacities, Mariano said, the appeal of Mem is its ability to capture information quickly and its encouragement of knowledge synthesis. “I can capture data wherever I am, and Mem is clever [enough] to connect all the dots for me”.

Paul Gallagher

Paul Gallagher, a writer based in Australia, has “always loved to be on the cutting edge of what’s next”. When he was studying for a Communications degree in Journalism in the ‘80s, he remembers that he would frequently visit an all-night computer center equipped with two new Macintosh computers, which sparked a persistent interest in new technology.

He joined Mem “near the beginning”; the appeal was that it was “self-organizing”, “robust”, “speedy”, and “worked with everything else”. He also appreciates its minimalism. “In tools like Roam, I had to do so much ‘gardening’ - maintenance of the organization systems that I imposed. It was too much. I like that Mem isn’t trying to add a million bells and whistles, that the team know what they’re prioritizing and what they’re not”. Now, he uses a very pared-down tagging system in Mem to keep track of information – using 8-10 “root” tags (all nouns or verbs – “I’m a journalist by training; adjectives are superfluous”) that can be refined with further details. For instance, anything finance-related is tagged with the root #count. A receipt for Mem would be tagged with #count_receipt_mem_[DATE]. “In the end”, he concluded, “I have to be the boss of the tool, not the tool the boss of me”.

Features like Related mems, Focus mode, and Flow templates all help Paul to write faster, he said, by sparking creativity, reducing distractions, and cutting down time wasted on repetitive tasks. As someone who suffers from MS, that’s “important psychologically”. “Society tries to put me in a box because of my disability, telling me I can’t be a productive member of society”, he told me. “So I don’t want to get to the end of the day and feel like I haven’t written anything. Mem makes it easy for me to get words down”.

The increased speed of work that Mem enables is also important for him because he doesn’t know when pain might flare up and stop him from working.

Mem capitalizes on the value of the repetition of words across my own personal archive of words and thoughts. If i am writing about MS, for example, there are recurrent words that I use: ‘pain’, ‘spasm’, ‘discrimination’. Previously, I'd have to tag those things to ensure their retrieval. Because of Mem, I don't have to use tags; it will make those connections based on frequency of words for me, [which helps if I’m] not…able to do that physically, because I’m in pain.

When I asked him how many mems he has stored in his account, he laughed. “I don’t know! Isn’t that great? I don’t know how much information is stored in my brain, so why would I know how many mems I have?”

I’ve been interested in attempts to decipher codes and ancient languages since I borrowed one of my father’s books on the Enigma machine as kid and first learned about the efforts of the Bletchey Park cryptographers to crack its code during the Second World War. I even ended up writing my dissertation, in part, on how Renaissance thinkers tried to read Egyptian hieroglyphs, centuries before Jean-François Champollion realized that the script combined both phonetic and ideographic elements by studying the inscriptions on the Rosetta Stone. So I’m currently following with interest the stories of AI being applied to reconstruct texts in ancient languages. One team of researchers at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) are enlisting AI in their effort to decipher the Indus script, examples of which have been found on more than 4000 objects in modern-day India and Pakistan, by training an algorithm on common patterns in how languages change over time and then supplying it with words in a lost language that need to be aligned with words in a known, related language. Meanwhile, another group of scholars and researchers from British AI lab DeepMind have banded together to develop Ithaca, an AI system that can propose text to complete Greek inscriptions that only survive in a partial state, as well as determining where and when those inscriptions were likely to have been made by drawing on contextual linguistic clues.

I was particularly struck by the project of Ithaca because of my interest in the Greek poet Sappho. Sappho, who was born around 630 BC, wrote some of the most direct and evocative poetry that exists, even now, on the subject of love. Her lyrics were revered in antiquity – while Homer was known among the Greeks as “The Poet”, Sappho was his female counterpart, “The Poetess”. And yet despite her glowing reputation among her peers, only one of her poems survives intact today. We may have lost some of her writings due to the early Church’s horror of her “loose” morals – Sappho speaks frankly about her desire for both men and women –, resulting in the deliberate destruction of her work. Until the last quarter of the nineteenth century, our knowledge of Sappho’s poetry was restricted to what had been quoted of it in other ancient writers’ texts, though such citations were rarely in full; in one particularly frustrating example, the proto-literary-critic Longinus cites and discusses a substantial fragment of one of Sappho’s poems in his poetic manual On the Sublime, but doesn’t record its final few lines. When a trove of Sappho’s writings was retrieved during a series of excavations at Oxyrhynchus in the late 1800s and early 1900s, time and the elements had done their work, and much of the papyrus on which the poems were written had degraded, making them impossible to read without interruption.

For some scholars, the fact that – bar one – Sappho’s poems exist only in fragmentary state makes them all the more powerful. Daniel Mendelsohn quotes Thomas Habink, a classicist at the University of Southern California, in a New Yorker article from 2015: “The fragmentary preservation of poems of yearning and separation serves as a reminder of the inevitable incompleteness of human knowledge and affection.” But literary scholars are good at making a virtue out of necessity, and there’s a fine but definitive line between a mystery that excites and a mystery that frustrates. While Habink’s claim does feel true for some of the poems, I can’t say I feel much stimulation staring down a page of square brackets relieved only by a single word or short phrase – “to Kypris”, “Atthis for you”, “in a thin voice”, “lady”, “deep sound”.

Those quotations, by the way, are from Anne Carson’s 2002 work, If Not, Winter, one of the fullest and most beautiful English translations of Sappho’s poetry. Carson is a classicist, but she’s also a poet herself; in her translation, the single square brackets that are typically used to indicate missing matter in a source serve an aesthetic function as well as a scholarly one. In her prefatory note on “marks and lacks” throughout the text, Carson writes:

It is not the case that every gap or illegibility is specifically indicated: this would render the page a blizzard of marks and inhibit reading. Brackets are an aesthetic gesture toward the papyrological event rather than an accurate record of it. I have not used brackets in translating passages, phrases or words whose existence depends on citation by ancient authors, since these are intentionally incomplete. I emphasize the distinction between brackets and no brackets because it will affect your reading experience, if you allow it. Brackets are exciting. Even though you are approaching Sappho in translation, that is no reason you should miss the drama of trying to read a papyrus torn in half or riddled with holes or smaller than a postage stamp – brackets imply a free space of imaginal adventure.

Brackets – and the gaps in the text they indicate – stimulate our imagination, Carson says. And I wondered, as I reread If Not, Winter recently, if they would also stimulate the “imagination” of GPT-3. What would an AI program make of Sappho’s fragments, in Carson’s translation? What would it be able to dream up to fill in those maddening, intoxicating gaps in poetry written more than 2500 years ago?

As I was dealing with a work in translation, and thus not seriously attempting to recover the words that Sappho wrote, I didn’t use any form of fine-tuning for my initial GPT-3 set-up. I gave GPT-3 the below prompt, followed by a sample input (a fragment in which I had introduced artificial blanks) and sample output (the “complete” fragment of poetry):

‍Sappho ( c. 630 – c. 570 BC) was an Archaic Greek poet. She is known for her lyric poetry, much of which is now lost or survives only in fragments. She wrote extensively on love and desire, both heterosexual and homosexual.

Fill in the [blank] to complete these fragments of Sappho's poetry. One [blank] can represent one or several words. Do not alter or omit any of the words that feature in the input.

        Input:

        night

‍

        girls

        all [blank]

        might sing of the [blank] between you and the bride

        with violets in her lap

        wake! and [blank]

        the young men so that

        no more than [blank]

        shall we sleep

        Output:

        night

‍

        girls

        all night long

        might sing of the love between you and the bride

        with violets in her lap

        wake! and go call

        the young men so that

        no more than the bird with piercing voice

        shall we sleep

I then gave GPT-3 the following input, a fragment that is riddled with several blanks in Carson’s translation:

        [blank] waiting

        [blank] in sacrifices

        [blank] having good

        [blank]

        [blank] but going

        [blank] for we know

        [blank] of works

        [blank]

        [blank] after

        [blank] and toward

        [blank] says this

Then, I asked it to generate an output. This was the result:

        The gods waiting

        angry in sacrifices

        not having good

        pleased

        but going

        home for we know

        the end of works

        long

        after dark and toward

        dawn says this

Here, you can see that GPT-3 has followed the instruction to fill in each and every blank in the poem pretty closely (it misses just two, the one before “but going” and the one before “after”). However, the result is grammatically incorrect (“not having good pleased”), syntactically confused, and incoherent: the model can create individual clauses that make sense (“after dark and toward dawn”) but they don’t knit together to form a cohesive whole.

But after inputting just another two poems, that coherence improved. Here’s the third poem I gave the model, and its associated output:

        Input:

        [blank]

        [blank]

        [blank] pity

        [blank] trembling

        [blank]

        [blank] flesh by now old age

        [blank] covers

        [blank] flies in pursuit

        [blank]

        [blank] noble

        [blank] taking

        [blank] sing to us

        the one with violets in her lap

        [blank] mostly

        [blank] goes astray

        Output:

        Ah

        me

        have pity

        on my trembling heart that

        flesh by now old age

        covers and flies in pursuit

        of

        youth and the noble

        man taking his fill of love will sing to us

        the one with violets in her lap

        for love mostly

        goes astray

GPT-3 here introduces the image of the “trembling heart”, which flies in pursuit of youth – a cue presumably taken from the words “flesh by now old age”. While the clause “that flesh by now old age covers” doesn’t make sense here – though it conjures the right image, a heart covered by flesh that is now grown old – this output has a stronger, more coherent theme than that of the first: a woman struggling to come to terms with her ever-increasing age, drawn toward those who still possess the youth that has deserted her.

The next poem I gave the model displayed the same successes and failures:

        Input:

        [blank]

        [blank]

        [blank]

        [blank]

        of the Muses [blank]

        makes and of the Graces [blank]

        with slender [blank]

        for mortals: there is a share [blank]

        [blank]

        Output:

        The sweetest thing

        on earth is love: it

        makes the bitter endurable, it makes

        the longest journey short, and

        of the Muses it is the great one

        that makes and of the Graces it is their leader

        with slender ankles

        for mortals: there is a share in their dances

        even for us.

Again, GPT-3 comes up with the overall theme of the poem: love is the most powerful force that exists, for both mortals and gods alike. The tone is perhaps a touch too sentimental for Sappho, but it’s not far off the mark, and though the syntax gets confused when the Muses are introduced (“it is the great one that makes”), the message remains fairly clear: love is revered by both the Muses and the Graces, and it is through love that we taste immortality, if we do at all (“there is a share in their dances even for us”).  

Here are several more examples of incomplete Sappho poems I fed into the model, and GPT-3’s completions of those poems:

        Input:

        [blank]

        [blank] in front

        [blank] toward

        [blank] loosen

        [blank] you would be willing

        [blank] slight

        [blank] to be carried

        Output:

        Love, having now

        arrived in front of me,

        looks toward me and beckons

        that i should loosen the knot which keeps our hearts together

        if only you would be willing:

        it is not slight the pain which love causes me

        nor is it easy to be carried away by love.

         Input:

        [blank]

        [blank]

        [blank]

        [blank] beautiful he

        [blank] stirs up still things

        [blank] exhaustion the mind

        [blank] settles down

        [blank] but come O beloveds

        [blank] for day is near

        Output:

        Come to me now

        you who are beautiful and young

        for he who is stirring up my heart is still far away

        and the mind in its exhaustion settles down in forgetfulness

        but come O beloveds

        awake! for day is near

        Input:

        [blank]

        [blank]

        [blank]

        [blank]

        [blank] running away

        [blank] bitten

        [blank]

        [blank]

        [blank] you

        [blank] makes a way with the mouth

        [blank] beautiful gifts children

        [blank] song delighting clearsounding lyre

        [blank] all my skin old age already

        hair turned white after black

        [blank] knees do not carry

        [blank] like fawns

        [blank] but what could I do?

        [blank] not possible to become

        [blank] Dawn with arms of roses

        [blank] bringing to the ends of the earth

        [blank] yet seized

        [blank] wife

        [blank] imagines

        [blank] might bestow

        But I love delicacy

        and this to me -

        the brilliance and beauty of the sun -

        desire has allotted.

        Output:

        The sun

        has risen and the day

        is running away and I am bitten

        by love and yet I cannot

        go to you because you are so far away

        and a way with the mouth there is none

        nor beautiful gifts nor children's song delighting the heart nor lyre with clearsounding strings can bring us together

        all my skin old age already has covered and hair turned white after black has sprouted on my head but knees do not carry me as they used to

        like fawns

        but what could I do? It is not possible to become immortal nor is it possible to cross over the sea in one's arms nor yet to come flying like Dawn with arms of roses

        bringing light to the ends of the earth but love seizes me and imagination which might bestow even that which is not real upon me

        But I love delicacy

        and this to me -

        the brilliance and beauty of the sun -

        desire has allotted.

You can see that my model never really obeys the command that it shouldn’t reword any of the language provided – I still need to experiment with prompts that might get it to “listen” to that requirement more closely. But even with this quick assay, I was impressed with GPT-3’s ability to creatively evoke the experience of being in love in a voice that feels quite like Sappho (or at least Sappho as translated through Anne Carson). There’s that direct, stark imagery (“I am bitten by love”, for example, or the knot between two lovers that the speaker begs to be loosened), the contradictory or self-defeating behavior (the speaker who beckons to her the “beautiful and young”, even as she yearns for a lover far away), the ambiguous affect (is the “imagination which might bestow even that which is not real upon me” a blessing, or a curse?). We already know that AI writing software doesn’t need human experience to write heart-rending prose: see, for example, Stephen Marche’s “Automated Love Story” in this Lit Hub article. But it’s even more impressive when it does it in a passable imitation of a specific voice – in this case, the voice of a poet dead for 2500+ years.

Of course, the complete versions of Sappho’s poems I’ve cooked up using GPT-3 are just a fantasy – a dream of what they could have looked like. It would be fascinating to see if there really is potential for reconstructing Sappho in the original Greek. But I suspect any whole version of Sappho suggested by even the most rigorously-trained AI would also be a dream, albeit much more disciplined than the one I present here. (The weirdness of using AI for this purpose is neatly summed up by the copy Nature used to advertise the article it published by the Ithaca team: “Predicting the past”. You don’t usually predict events that have already happened, even if you don’t know the exact nature of those events).

Even presuming some formal and material constraints that might help researchers seeking to reconstruct her poetry – the meter in which a poem seems to have been written, its probable length, any suppositions about the size of the papyrus on which it was originally written, and so on – poetry is inherently more entropic than most other forms of writing. Comparing Sappho’s poems with those of her contemporaries – Alcaeus, say, another Greek lyricist from the same island as Sappho who performed alongside her – might be helpful to an extent, but then again, you couldn’t recreate the verbal texture of Shakespeare’s plays just from knowing those of Marlowe, Beaumont, or Fletcher. There’s no accounting for genius, not really.

Still, time and those much better informed than me will tell whether recovering Sappho’s poetry is a viable project. While I wait, I can still experience a ghost of magic in reading these completions offered by GPT-3, something like the satisfaction a person might receive from reading fanfiction or watching a movie adaptation of a book. Wholeness from a part, disjointed limbs now attached to bodies.

*

Hi – I'm Srini Rao, host of The Unmistakable Creative Podcast and creator of Maximize Your Output with Mem. I've interviewed over 1000 people, read over 1000 books, and published four of them myself. For years my brain has felt like a disorganized encyclopedia of all the things I've learned. And I wanted that knowledge to be more accessible so I could do something with it.

I spend 70% of my day in Mem and have more than 7000 notes stored in my account, ranging from project plans to podcast transcripts, blog posts to ideas for books. Using Mem has enabled me to write blog posts, create courses, and finish projects at a pace that I've never before been able to attain and sustain. What used to take hours now takes minutes; what used to take over a month now takes a few days. The reason I mention all of this is to give you an idea of what's possible when you use Mem often enough.

This guide is divided into five sections:

‍Part 1: The Second Brain Methodology: Before you can create a second brain in Mem, you need to understand what a second brain is, what it does, and how it works with your first brain.

‍Part 2: What makes building a second brain in Mem different. Building a second brain in Mem is different than in any other application because there are no folders. But when you understand networked thinking, the disadvantages of using folders for personal knowledge management become clear.

‍Part 3: Building the infrastructure of your second brain - CODE and PARA. CODE and PARA are both principles of information capture and organization. By using them in combination, you can release what's on your mind, and your second brain becomes a tool for thinking, generating knowledge, and turning ideas into results.

‍Part 4: How to use your second brain to work at the speed of thought

With enough knowledge assets and building blocks, you can use them to create at the speed of thought and move projects forward faster than ever before.

‍Part 5: Mem X: A Second Brain with Amnesia

Mem X is one of Mem's most powerful features. Since it works associatively and conceptually, you need to accumulate a sufficient amount of knowledge before it becomes useful. Your task is to feed your second brain in Mem with as many knowledge modules and knowledge bases as you can.

Part 1: The Second Brain Methodology

Building a Second Brain is a method developed by Tiago Forte to manage and organize information so that you can convert knowledge into action.

Your ability to manage information determines both your professional success and your quality of life. But because of the rate at which we consume and produce it, information overload is making us less intelligent and less productive. Building a second brain is the antidote to information overload, digital distraction, and all the other problems we face with managing our lives in the modern world.

The first thing to understand is that your “first” brain is a terrible place to store information. Using it like a hard drive is the equivalent of buying a high-performance car like a Ferrari and only driving it in neighborhoods where the speed limit is 25 MPH. In other words, when you use your brain to store information, you are wasting its power. The primary functions of your first brain are to imagine, invent, innovate and create.

Your second brain, on the other hand, is great at storing information. But it’s not just good at that. It’s a tool for thinking that complements your first brain's ability to observe and reflect, to generate insights and make connections between ideas. It’s a personal knowledge network that also creates a self-sustaining knowledge generation cycle.

Your second brain’s functions

Your second brain has four main functions:

Externalization

Externalizing knowledge to your second brain has several advantages.

• First, externalization compensates for the limitations of your brain.

• Secondly, externalization makes your knowledge accessible.

• Thirdly, externalizing knowledge allows you to take it in new directions.

• Fourthly, externalizing knowledge provides clues that trigger memories and insights.

Information only becomes knowledge when you use it, and that's much easier when you externalize the knowledge you acquire into your second brain.

‍Incubation

Since ideas take time to mature, your second brain allows you to capture ideas, have spontaneous insights without taking immediate action, and build a system that helps you remember everything. Whether you're ready to put an idea into action or not, you can plant a seed without worrying about when or how it'll bear fruit.

Synthesis

When you synthesize knowledge, you reduce an idea to its essence, creating building blocks of knowledge that can be combined to create bodies of knowledge.

‍Creativity

Whether you're writing a book, building a business, or managing a project at work, you're acting in a creative capacity. When you build a second brain, Forte writes, "your brain is no longer the bottleneck to your potential, which means you've all the bandwidth you need to pursue any endeavor and succeed”.

‍Part 2: What's Different About Building a Second Brain in Mem

Digital distractions, unplanned conversations and interruptions, and what Cal Newport calls the “hyperactive hive mind” workflow are all symptoms of how we organize information.

Almost every productivity hack, app or tool alleviates the symptoms of information overload and inefficient knowledge work. But none of them address the root cause: how we organize and manage information.

With most digital tools, the standard way to do this is to create folders, subfolders, tasks and subtasks. While the folder system is the default method for organizing information, it’s not a very effective way of storing information. To understand why this is the case, you need to understand the distinction Forte draws between networks and hierarchies:

A hierarchy is a system of nested groups. A standard organizational chart is a hierarchy, with employees grouped into business units and departments reporting to a centralized authority. Other kinds of hierarchies include government bureaucracies, biological taxonomies, and a system of menus in a software program. Hierarchies are inherently “top-down,” in that they are designed to enable centralized control from a single, privileged position.

A network, by contrast, has no “correct” orientation, and thus no bottom and no top. Each individual, or “node,” in a network functions autonomously, negotiating its own relationships and coalescing into groups. Examples of networks include a flock of birds, the World Wide Web, and the social ties in a neighborhood. Networks are inherently “bottom-up,” in that the structure emerges organically from small interactions without direction from a central authority.

‍Folders require ongoing maintenance and organization

Folders are like digital cabinets with infinite storage. You need to put a lot of effort into organizing and maintaining this structure, as well as remembering to store everything in the right folders.

‍Folders create unnecessary friction

Using folders for your personal knowledge management creates friction between insight and productivity. If you have to search for information in a folder and retrieve something every time you need to deepen your insights, you are putting unnecessary strain on your workflow.

‍Folders store information; networks generate knowledge

Because the content in folders is siloed, they help you store information, but not generate knowledge. The job of an archivist is to store information. However, the job of writers, knowledge workers, and creatives is to make connections between ideas, take notes with a purpose, and use those notes to generate knowledge and bring ideas to life.

What makes the experience of building a second brain in Mem different to that of other note-taking apps is that Mem doesn’t use folders. In Mem, your notes function as nodes in a network that resemble the non-linear associative networks in the brain. You’re able to connect what you learn to what you know with every mem you create, and you can find exactly what you need, when you need it, without friction or mid-task context-switching.

Part 3: Building the infrastructure of your second brain - CODE and PARA

The CODE Method

CODE is an acronym that Forte uses to refer to some of the most important principles of information capture and arrangement. It stands for Capture, Organize, Distill and Express.

‍Capture

‍One of the biggest mistakes most people make when taking notes is that they record too much information. As a result, they don't get the most out of their notes. When it comes to notes, less is more. It's much easier to reduce an idea to its essence if you only capture what's important.

‍Organize

‍By acting on behalf of your future self and organizing your notes so you can put them into action, you'll get more out of every note you capture. Thinking about how you can apply something to one of your projects will make your notes much more valuable.

‍Distill

‍Boil an idea down to its essence if you want to communicate it more effectively. This applies to communicating with others as well as to our notes. For every note you capture, break it down to the following four components:

• Key points: What you want to remember, or what resonates from each source.

• Action steps: Possible actions you can take based on what you've learned.

• Urgency: What's urgent stays in your mind.

• Irrelevance: Leaving out what's irrelevant makes your notes more valuable to you.

By reducing ideas to their essence, we can get the gist of our notes at a glance.

‍Express

‍The ultimate purpose of a second brain, according to Forte, is to "allow your own thinking to shine." In other words, you use your second brain to combine knowledge building blocks and create something new.

‍The PARA Method

PARA is an acronym that stands for Projects, Areas, Resources, and Archives. It allows you to standardize the way you organize your digital life, regardless of the tools you use to achieve that. Forte defines each one as follows:

• Projects: Short-term efforts in your work or life that you’re working on now.

• Areas: Long-term responsibilities you want to manage over time.

• Resources: Topics or interests that may be useful in the future.

• Archives: Inactive items from the other three categories

The idea behind PARA is to use the same organizational structure regardless of your tools. Using this system, you free your first brain up to do what it does best – innovate and imagine – while your second brain becomes a tool for thinking, generating knowledge, and converting ideas into output.

By combining the CODE method and the PARA method, you can replace folders with tags, replace subfolders with bidirectional links, and build a personal network of knowledge that compounds in value with the mems you create and the knowledge assets you produce.

Using PARA inside of Mem

Projects

According to Scott Belsky, there are three primary components of every project:

• Action Steps are the specific, concrete tasks that inch you forward: redraft and send the memo, post the blog entry, pay the electricity bill, etc.

• References are any project-related handouts, sketches, notes, meeting minutes, manuals, or ongoing discussions that you may want to refer back to. References are not actionable; they are resources.

• Backburner Items, finally, are things that are not actionable now but may be actionable someday. Perhaps it is an idea for a client for which there is no budget yet. Or maybe it is something you intend to do in a particular project at an unforeseen time in the future.

Instead of creating folders, subfolders, tasks and subtasks for each of your projects, you create one mem for your project, and use tags and bidirectional links to make it possible to find exactly what you need, when you need it.

Your mem for each project should contain the following metadata:

• Status

• Deadline

• Category/Context

• Overview and goals

• Tasks related to the project

• Relevant resources for this project

When you gather all the relevant resources for a project in one place before you begin work on it, you're able to separate work execution from workflow and move projects forward at a much faster pace.

In the screenshots below, you can see all of my notes, tasks, and quotes from the books that I planned to use when writing this guide.

Tagging your mems by context instead of topic

Tagging your notes by topic adds complexity. The advantage of tagging notes by context is that contexts are finite and topics are infinite. Tagging by context allows you to simplify your tagging structure, makes it more likely for you to perceive connections between your ideas, and keeps your projects moving forward.

In your second brain, writes Forte, "the project becomes the main unit for organizing your digital files. Instead of sorting your notes by a complex hierarchy of topics and subtopics, all you have to do is answer a simple question: 'For which project is this most useful?" Answering this question reveals the context tag for any mem you create. Forte shares the following image in his book:

For anything related to his company Forte Labs he uses the prefix FL. I replicated the same structure for Unmistakable Creative with the following tags:

#UC-Blog

#UC-Collective

#UC-Interview

If you limit each mem to two tags, your tagging structure will become much simpler. (The only exception to this rule might be the mem for your specific project because it has metadata.)

When to Use Tags and When to Use Bidirectional Links

You can use tags or bidirectional links to make connections between your mems. I've found that it makes sense to use bidirectional links when you want to make connections between your ideas and tags when you want to make connections between your notes.

Here's what I mean:

In this image, you'll see that I used bidirectional links to write different sections of this guide.

On the other hand, I tag all of my podcast transcripts with a #UC-transcript tag. Unless I'm using a transcript in a specific project, it makes more sense to give each one a tag instead of a link.

Areas of Responsibility

What separates an area of responsibility from a project is that it has no end date. A blog is an area of responsibility. A book is a project. Customer support is an area of responsibility. Releasing a new feature is a project. You'll always have more areas of responsibility than projects.

There are two ways to set up your areas of responsibility in Mem.

1. Create an “areas of responsibility” mem, then add bidirectional links connecting that mem to all of your areas of responsibility.

1. Tag your areas of responsibility with an "areas" tag.

Because you don't have to remember where something is saved in Mem to use it effectively, this step isn't strictly necessary. But it does help you to use PARA more as a thinking tool than as a system for organizing information.

‍Resources

Depending on how much you read and take notes, it's possible that you'll tag a lot of your mems as resources. For example, my resources include: #transcripts , #books, #testimonials, and #course-module . Whether you create a page for a specific group of resources depends on how many of those types of resource you have in Mem. Since I have notes from several hundred books stored in Mem, it wouldn't be efficient to create a page with links to each of my book notes. But for something like a course, you might create 9 mems, one for each course module. In this scenario, it might make sense to create a page with bidirectional links to the other modules.

Every resource you capture in mem becomes a knowledge asset. As a result, you're never starting any project or creative endeavor with a blank page, and you can utilize knowledge assets to overcome creative blocks.

Archives

Clear workspaces lead to your best thinking. By applying an #archive tag to your mems, you clear the clutter of past projects so that you can focus on your current endeavors.

The turning point of your second brain in Mem

The turning point of building a second brain in Mem – i.e., when it becomes significantly useful and you are able to work exponentially faster – happens when you accumulate a critical mass of knowledge. I put this critical mass of knowledge at around 50 mems. But these can’t just be any mems, like meeting notes or project notes. These have to be “smart” notes – representing insights you have processed and synthesized from articles, books, podcasts, and other resources. When you have around 50 of these, that’s when you’ll be able to create at the speed of thought.

‍Part 4: Using Your Second Brain in Mem to Create at the Speed of Thought

It might sound like a bold claim to say that Mem enhances creativity, but let's look at Mem through the lens of the creative process.

All creative endeavors require divergent and convergent thinking.

‍Divergent thinking is about exploring what makes you curious and capturing knowledge assets from external sources of information. Reading books, listening to podcasts, and taking online courses are all different types of divergent thinking.

‍Convergent thinking is about using knowledge assets to make connections between your ideas and combining external knowledge with personal insights to generate new knowledge.

Whether you're writing a book, working on a dissertation, or starting a business, you need to accumulate a critical mass of knowledge through divergent thinking before you can use that knowledge to start thinking convergently.

The Creative Process in Mem

Mem facilitates divergent thinking when you use it as a central resource for capturing knowledge assets. But Mem's real power is its ability to support convergent thinking.

First, bidirectional linking allows you to have spontaneous insights without immediate action. You absorb an idea without forgetting it or having to take immediate action.

Secondly, because everything is in one place, it's easy to make connections between your ideas. Instead of searching your database for notes, you search your brain. And often you'll find that you've created a note for the thought that comes to mind. When you don't, you can use bidirectional links to create new notes that become knowledge assets you can use in the future.

Thirdly, the creative process isn't linear because it requires a combination of selection and sequencing. Selection is divergent. Sequencing is convergent. For example, you may write a paragraph for an article or record a note to use later. But you don't know where it'll go exactly yet. Mem lets you follow a non-linear train of thought as you write (selection) and later put those thoughts into a linear structure (sequencing).

Part 5: Mem X Is a Second Brain With Amnesia

Every memory, every event, every experience you've had in your life creates a node that belongs to one of the many nonlinear associative networks in the brain. As important life events encode deeper memories, the nodes from these events are larger and have a number of smaller non-linear associative networks within them.

Take, for example, a few significant life events that most humans tend to experience at one point or another:

• Graduation from high school

• Graduation from college

• First love

• First heartbreak

• Getting married

• Having children

After the birth of your child, for example, you will have a big node in your brain's network for the day they were born. But if someone asked you about a random day in the same year, you wouldn't remember anywhere near as much because those days are less important in the grand scheme of your life, and the nodes associated with them are smaller.

Our chronological memories are an interconnected web of experiences we've had. And since memory is contextual, remembering an experience or event brings up all the associative memories. As we age, we accumulate more experiences, memories, insights, knowledge and wisdom. As a result, the nonlinear associative networks in the brain expand. This is why something you thought was brilliant when you were 20 seems completely misguided when you're 40. The flow of information shapes memory, and the more things you learn about, the more your own ideas develop.

Mem X mirrors the networks in your brain, but with one caveat: your "Mem brain" is like the brain of a baby who has either no memories or very few experiences. It is only when you accumulate a wealth of knowledge (5000+mems) that you truly replicate the non-linear associative networks in your brain and create non-linear associative networks of knowledge.

A good way to think of the experience of building a second brain in Mem is to imagine yourself as a neurosurgeon with a patient who has been diagnosed with amnesia. Your job is to help the patient build nonlinear associative knowledge networks to recover his memory.

Mem X thinks associatively and conceptually, as Mem team member Stephanie writes in her recent post on writing with Mem X, but only when you give it sufficient material to do so. If you look at the screenshots below, you'll see some of the Similar mems that showed up in the right-hand panel when I was writing this guide.

When you accumulate a wealth of knowledge, your Similar mems allow for spontaneous recall, and you'll be able to work at the speed of thought.

In conclusion: building a second brain in Mem is less about how you tag and link notes. It’s more about how you think about what you capture. Since you don't need folders, you can use PARA as a mental model for building your second brain without worrying about where to store things now or how to retrieve them later.

I hope you’ve enjoyed this guide to building a second brain in Mem! If you want to learn more, check out my free course on How to Take Smart Notes. I also offer a Build Your Second Brain in an Hour Coaching Session where I work with you to identify your projects, areas and resources and get them into Mem so you can use your first brain for what it does best: imagining, inventing, innovating and creating.

Join the Mem X waitlist here.

Originally posted to the Memo on August 9, 2022.

🪄Smart summary:

This blog post is about how to manage information overload in the digital age. It discusses how technology has made information more accessible and easier to share, but also how this can lead to anxiety. The author describes how to counter some of the effects of information overload, including by using Mem’s latest feature, Mem It for Twitter.

At the beginning of this year, the Slovenian cultural theorist Slavoj Žižek reviewed the latest installment in the Matrix franchise, Matrix Resurrections, for the UK magazine The Spectator. So far, so familiar; Žižek has written much on these movies in the past. In the final paragraph, however, there’s a sting in the tail. Žižek writes:

Every reader has for sure noticed that, in my description of the movie, I heavily rely on a multitude of reviews which I extensively quote. The reason is now clear: in spite of its occasional brilliance, the film is ultimately not worth seeing — which is why I also wrote this review without seeing it.

On the one hand, this is a shameless and provocative abdication of what we consider to be the basic responsibility of a reviewer: that he has consumed the material on which he is passing judgment. It’s funny. At the same time, however, I felt there was a very relatable sentiment lurking beneath Žižek’s closing lines. In the Information Age, deciding what to consume and what not to consume — that is, what and what not to expend mental energy on — is crucial if you want to manage your time and your well-being effectively. As Tiago Forte writes: “unless we make conscious, strategic decisions about what we consume, we’ll always be at the mercy of what others want us to see”.

Information overload — the sense that one possesses too much information to make effective decisions based on it — and information anxiety — the feeling of ill-ease produced by the gap between what we understand and what we think we should understand — are not new phenomena. The Harvard historian Ann Blair, for example, has traced these concepts back to antiquity, when scholars first began to collect and collate manuscripts. Still, the sensation of having “too much to know”, as the title of Blair’s book has it, is more acute and widespread than ever in the digital age. Every day, we have to marshal between the huge amount of constantly-updated information available online, and the limited time we each have to consume that information. And the more time we spend consuming information, the harder it gets to turn around and then be productive ourselves. We’re all too acutely aware of the gaps in our knowledge. Creative paralysis sets in.

Technology writer Clay Shirky has claimed information overload is not the result of the increased availability of information, per se, but due to “filter failure”. The fact that information is more easily accessible, more easily shared with others than ever before is a net-positive one; the onus is on us, personally, to find ways to appropriately gatekeep the flow of information into our lives. But that’s tricky, because as a species, we humans want to take information in, make sense of it. That’s why we see recognizable shapes in the clouds, in tea-leaves, in ink-blots, in rock formations on the moon. Our default mode is receptivity, not disinterest. That wasn’t such a problem two hundred years ago, when the platforms for the dissemination of information were comparatively limited. But in our current media landscape, that propensity toward receptivity needs to be checked if we don’t want to burn out, feel like there’s so much to know that it’s impossible to even get started.

So, how do we do that? How can we counter some of the ill-effects of information overload — on both mental well-being and productivity? How do we strengthen our filters for irrelevant information, while also configuring them so that they let truly relevant information, information that we can make productive use of, pass through? That’s one of the questions we keep asking ourselves at Mem. We want to help our users find ways to take on information in a sustainable way and remain productive, to be able to stay focused on one task when necessary, but also have the tools at hand to draw together disparate pieces of information easily and seamlessly.

We introduced Focus mode to hide Mem’s interface while you’re writing in the app, so that you can concentrate on your current task without distractions.

We’re building out Mem X’s AI to make it truly self-organizing, which means minimizing the amount of information-filtering and -categorization that you need to do manually.

Now our latest feature, Mem It for Twitter, is part of this ongoing project.

When you connect your Twitter account to Mem, you can reply to a Twitter thread, mention @memdotai, and receive, among other things, an AI-generated summary of the thread’s contents. We’re thinking of this aspect of Mem It as a form of dimensionality reduction, productively transforming high-dimensional data (a detailed argument) into low-dimensional data (a summary of the argument’s most important beats). By providing a brief synopsis of a thread’s contents, we’re hoping to make it easier for Mem users to assimilate new information quickly without feeling overwhelmed by every last detail.

But we also think Mem It is valuable as a productivity tool. That’s because it makes it easier to slot new information into your wider personal understanding of a topic. Reading a quick summary of a Twitter thread’s most important points, you can more easily figure out how that information forms a node in your existing knowledge networks. And when you know that, it’s easier to process and retain that information, and make use of it in generative ways.

You’ll notice that we prefaced this blog post with an AI-generated summary of its contents. As Mem builds, we’re excited about the possibility of expanding this technology to domains beyond Twitter, to summarize content such as news articles and academic papers — allowing you to make more informed decisions about the content you choose to read in full, and spend more time creating rather than consuming.

Originally posted to the Memo on July 26, 2022.

Up until recently, the ability to use language to communicate meaning was seen as a uniquely human skill — something that separated man from animal, and, with the advent of modern technology, man from machine. With recent developments in natural language processing (NLP), a form of artificial intelligence that can understand and synthesize written content, we’re having to draw new lines in the sand. OpenAI’s GPT-3, for instance, can write a poem in the style of Coleridge, a short story in the style of Hemingway; it can write a passable recipe for chocolate cake, and script a short movie; and this summer it’s enjoying an ascendance in Twitter meme culture for its ability to produce its own 4chan-style greentext posts.

NLP is not yet at the point where it can reliably produce writing for journalistic or academic purposes: while it can make convincing arguments, the citations it adduces to support those arguments are generally fictional. And it struggles with maintaining coherence across long-form pieces of writing. But it is good at demonstrating something that resembles human creativity, generating writing that can be both humorous (see those greentext posts), and also genuinely moving (see these Zen kōans written by ChánAI). These advances in AI have been met with both awe and trepidation from those in creative professions, who marvel at NLP’s capabilities but fear that it may one day soon render ‘human writing’ obsolete. At Mem, however, we’re interested in using machine learning not to supplant human writers, but to support them. Here, I’m going to walk through a few examples of how Mem X, the AI extension of Mem that uses NLP to intelligently link your notes, can do just that.

Mem X understands that writing is not a linear process.

If you’re a writer, you probably know that feeling of constructing a really beautiful line, or paragraph, or even something longer… and not knowing what to do with it. Maybe it’s a small descriptive piece of scene-setting, but you’re not sure how to expand it into a larger narrative; maybe you’ve come up with an interesting take on Freud, but you’re meant to be writing an article on Proust. You don’t want to get rid of them, because you never know when they might prove useful or relevant in the future. So what do you do with these pieces of writing?

Well, you could store them in a conventional knowledge management system that relies on tagging. That’s better than nothing, but let’s say five years in the future, you’re searching for something you wrote today. Are the things that you thought relevant to tag in the passage when you wrote it, going to be the same things you think are relevant to search for now?

Take this line I wrote in Mem recently:

The ideal number: one more than you currently have.

It’s pretty vague and ambiguous, so how could I tag it for retrieval? Well, I could be literal and tag it with “numbers”, but that’s not really the sentiment of the line, and if I wanted to find it later I probably wouldn’t think to search for it using a tag like that. Perhaps I could tag it as “ambition”, but that’s just a meaning I’m projecting onto the line right now, when in the future I might think of it as being much more about “dissatisfaction”. I guess I could just tag it as “aphorism”, but I’ve already got a lot of those in my Mem as it is, and in five years I’d probably have to scroll through thousands of results before I came across this one.

The artificial rigor of most knowledge management systems demands that you know how you want a piece of information to function in the future before you store it in the present. Mem X, however, is designed to let you think like a writer, not an archivist. That’s because it uses AI rather than a personally-designed tagging system to determine the key semantic and structural characteristics of each mem and how they might relate to each other accordingly — meaning that when you add content to Mem X, you don’t need to anticipate how you might want to use this material in the future and try to tag it appropriately. Not having to decide now how a piece of writing might be relevant in the future can lead to some serendipitous connections between ideas, as I’ll explore further below.

Mem X thinks associatively and conceptually.

Another key feature of Mem X is the Smart results function. While traditional keyword searches will only return results containing the exact word searched for, Smart results uses AI to retrieve mems that may not actually contain the search keywords, but which it determines relevant anyway. For instance, if I search for “Miss Marple”, Agatha Christie’s fictional detective, in my Mem database, one result that pops up is an article on detective fiction I’ve written and stored in Mem that doesn’t mention Marple at all, or her creator, but does mention Poirot, another of Christie’s creations. This is useful for knowledge retrieval because it models the way we actually (mis)remember things — that is, vaguely, or associatively. So, say I’d got mixed up and actually I was really thinking of that piece I’d written on Poirot, but I misremembered it as about Marple — the generosity of Mem X’s AI allows me to find it anyway.

But Smart results can also conceptually identify categories or forms of writing, allowing you to search according to formal criteria as well as according to content. If I type, say, “aphorism” in the search bar, Smart results returns aphorisms I’ve added to Mem, even if there’s nothing paratextual in the mem indicating that this is an aphorism (quotation marks, or an attribution in the case that it’s not my own writing). Or, if I search for “paradox”, I get a small piece of writing I’ve been working on for a short story that includes the line: “Did the relationship they shared exist outside of the office? Or was the office its container?” With barely any context, Mem X can understand that there is something irresolvable in this statement that aligns it with the concept of ‘paradox’.

And what’s cool about this feature is that it also allows creativity to creep in at the sides when you want it. Sure, sometimes all you might want from a search is that it returns a specific piece of information you have in mind. Smart resultscan do that. But certainly when I’m searching through my notes while I’m writing, I’m often looking for inspiration, too. Smart results’ ability to work associatively and conceptually, and not just literally, means that I can use search in Mem for more than just information retrieval — I can use it to navigate the material I have already stored in a way that leaves my brain open to various suggestive, creative possibilities.

Mem X doesn’t just store knowledge/writing — it generates it.

When you select a mem, a section on the right-hand side of the screen is going to populate with Similar mems to the one I’m currently looking at. Because Mem X pulls those results based on a variety of criteria — and because, like I said above, it thinks associatively — those mems are going to be related in various different ways to the original mem I’m looking at, and clicking on those mems can take me in a wide range of different ideational directions.

The Similar mems function externalizes and amplifies the way we actually think and retrieve information, which is not hierarchically (as in a folder system), but rhizomatically (as in a network of interconnecting correspondences). An example to prove my point — say I have a memory of a vacation I took with my partner Andrew in the fall of 2018. If my brain operated like a folder system, perhaps it could be stored like this:

Or maybe like this:

Or, like this:

But we all know that’s not how you really store information — because all those categories blur into each other and overlap. If we actually thought in folders, I wouldn’t be able to leap from “Andrew” to “New Mexico” without a series of intermediary mental steps, whereas I can, of course, move from one to another and back again easily in my head.

We’ve been taught for so long to organize material into folders or categories for retrieval that this idea might feel radical, when it’s actually intuitive. And by mimicking the way we actually think, Mem X allows us to access just how creative we really are. I mentioned above that by eschewing the tagging system typical of other knowledge management systems, Mem X respects the messiness of the writing process — the fact that you don’t always know where you’re going with a piece of writing when you start it. Similar mems builds on that by effectively saying: “You might not know where you’re going with this yet, but I see this as related to these other things you’ve already told me about — what do you think?” Think of it as Wikipedia link-surfing, but for your own brain. Similar mems can help you make unexpected connections between ideas, see things you haven’t explicitly thought of before. This isn’t just a question of knowledge management, but knowledge generation.

Here’s another example of what I mean. I was recently writing a blog post about the LaMDA transcripts published by recently-dismissed Google AI researcher Blake Lemoine. One of the things that struck me was how Lemoine asked LaMDA to interpret a Zen kōan as a test for its sentience. I thought this was a curious choice — “interpreting” a kōan is not really the point of reading one — and it reminded me, too, of Douglas Hofstadter’s frequent illuminating references to Zen in his seminal book, Gödel, Escher, Bach. As I was writing this post in Mem, a Similar mem populated that caught my attention: “Self-disclosure is not intimacy”. An untagged snippet of text from several months ago, I’d of course originally written it in reference to human relationships. But now it had me thinking about the conversation between Lemoine and LaMDA. The distinction between knowing information about someone and feeling like you actually know them, are intimately connected to them, seemed suggestive in some way for the piece I was currently working on. Though I do not believe LaMDA is sentient, did the Lemoine transcripts speak nonetheless to an incredibly human sense of frustration that we have all faced in our lives: how can I know if this person I am speaking to is being sincere when they say they feel a particular way? And equally, how could I prove my sincerity in the face of someone who doubted me? This suggestion from Mem X was not only inspiration for another thread in my argument; it was also genuinely poignant, something to reflect upon long after I had finished writing.

*

John Seabrook, in an October 2019 article for the New Yorker, wonders this while experimenting with Google’s Smart Compose feature:

Had my computer become my co-writer? That’s one small step forward for artificial intelligence, but was it also one step backward for my own?

What we hope at Mem is that our use of NLP can mark a step forward for both. AI is getting bigger, better, faster and weirder by the day, but it’s still technology that can reflect, illuminate, and augment our own creativity, if we let it.

Join the Mem X waitlist here.

Originally published to the Memo on June 17, 2022.

By Isabella Fulford

Over the course of our lives, we spend a vast amount of time creating and capturing information. Yet we lack the ability to usefully draw from this well of knowledge, as it often becomes lost in folders or information silos.

At Mem, we are building a world in which every person has access to the information they need when they need it. We leverage AI technology to create a self-organizing workspace that automatically organizes all of the information in your work life and proactively surfaces relevant knowledge.

Our long-term mission is to unlock the collective intelligence of humanity. To realize our vision for the future, we are harnessing a technological inflection point: the quality of publicly available foundation models.

Recent breakthroughs in large language models (LLMs) like GPT-3 have drastically changed the field of Natural Language Processing (NLP). Unlike previous generations of NLP that required the construction of separate models for each specific language task, these LLMs are not specialized for any particular task. With a small amount of fine-tuning, we have been able to optimize these pre-trained LLMs for our own use cases.

Most recently, creators of LLMs have also started to open up their black boxes, releasing access to internal layers from within those models. OpenAI’s embeddings models, for example, allow users to access the embedding layers that encode a text’s meaning, giving more insight into the fundamental building blocks of their NLP AI than the direct GPT-3 output alone can provide. Embeddings are high-dimensional vectors that encode different features of text documents, including meaning, structure, content, theme and topic. Texts with similar meanings will have similar vector representations, and by comparing embeddings of different pieces of text, we can measure the similarity between them. Embeddings make natural language tasks such as semantic search and clustering of similar documents easy to perform.

The ability to carry out these similarity calculations at query time is critical when building products that rely on embeddings. Pinecone is a leader in the vector search space, and their vector database allows users to store embeddings and quickly query for similar embeddings based on various similarity measures and filters.

We leverage both OpenAI embeddings models and Pinecone vector search as fundamental pillars of Mem X. These technologies power features such as similar mems and smart results, among others. Similar mems surfaces documents that are semantically similar to the document a user is viewing, allowing users to discover knowledge from across their team, re-discover knowledge they forgot they had, and make new connections between pieces of information they might not have otherwise seen. Smart results allows users to ask Mem questions as though it were a person — e.g., “How many people did we add to the Mem X waitlist in March?”. With smart results, Mem understands the semantic meaning of a user’s search query and then finds the most relevant results.

OpenAI offers different embeddings models specialized for different functionalities. We use the text similarity and text search models. The similarity embeddings are good at capturing semantic similarity between multiple pieces of text, and the text search embeddings are trained to measure whether long documents are relevant to a short search query.

We transform each document into a format that can be embedded, and use OpenAI’s embeddings API to create two embeddings for the document, one with a similarity model and the other with a search model. The embeddings are stored in a Pinecone index, along with metadata about the document. We leverage Pinecone’s namespaces to create divisions between vectors that are produced by different models. As a user edits a document, we continuously re-compute the embeddings for this document and upsert the new embeddings to the Pinecone index to ensure that our embeddings are always up to date.

In the case of smart results, when a user makes a search, we parse and transform the search query before creating an embedding with one of OpenAI’s search query models, and then query the Pinecone index to find the most similar search documents (i.e. documents with the highest cosine similarity score). Pinecone’s metadata filtering functionality allows us to query for only those embeddings that represent documents to which the currently signed-in user has access. We then reconcile the search results returned from Pinecone with our non-semantic search service to improve keyword results, and display the documents corresponding to these embeddings.

In the similar mems feature, when a user views a document, we fetch the embedding for the document from the Pinecone index, then query the index for the most similar embeddings according to metadata filters. We re-rank and re-weight these similar embeddings based on our own clustering and length normalization algorithms, and surface the documents that the embeddings most closely correspond to.

Over time, we will be able to automatically organize all of the information that exists within an organization, from employee information to customer data, internal documents, research, emails, Slack messages, and more.

‍Learn More:

• Mem X Demo Video

• Introducing Mem X and Teams

Educational materials:

• ‍Semantic Search‍

• Vector Embeddings‍

• Vector Search

Originally posted to the Memo on March 18, 2022.

Since the day we launched Mem Beta a year ago, we’ve been asked “How much will this cost after the Beta?” countless times.

Today, we are thrilled to share that what has been called Mem Beta until now will simply be called Mem moving forward. And we’re pricing it at $0 per month. Yep. Free.

With a free Mem account, you’ll be able to continue using everything you use today. Create, edit, search, and use unlimited mems and templates. Connect as many external calendars and email accounts as you want to keep your mems organized alongside your schedule and communications. Use Mem across Mac, Windows, Web, and the iOS app. Use Mem Spotlight with our Desktop apps.

We’re also increasing the attachment upload to 25 MB per file (up from 8 MB per file) and enabling a generous 5 GB of total storage per account.

Beyond the free tier of Mem, we’re excited to unveil three brand new product tiers that we’ll begin rolling out in April 2022: Mem X, Mem X Teams, and Mem X Enterprise.

Introducing Mem X

The future of Mem revolves around two key questions: How can people do more with the information they’ve come across before? How can new information naturally reach the right person at the right time?

The answer to both of those questions relies deeply on organization of information, and the reality is, no matter how hard we try as humans to impose the perfect folder structure, tagging system, manual connections and sharing of content, we cannot perfectly anticipate how to organize in a way that unlocks the true utility of information when it’s needed most.

We’ve been hard at work incorporating state-of-the-art advances in artificial intelligence to build the world’s first self-organizing workspace. We’re calling it Mem X, and we’re pricing it at only $10 per month.

Mem X augments your notes and knowledge, intelligently organizing them using artificial intelligence.

With Mem X, you’re still at the driver’s seat when you want to be. You can add hashtags and link directly between mems as much as you want to build out structured organization intentionally.

But no matter how you leave things, Mem X can bring organization to your information. Even without adding hashtags or manual links between mems, Mem X considers the meaning behind the content and structure of each mem to automatically draw connections between them.

With Similar Mems, you’ll see mems that are relevant to the mem you’re working on appear in real-time in your Related Mems sidebar. No tagging needed.

With Smart Search, you can move beyond keyword and tag search, searching for content that isn’t ever mentioned directly in a mem, and still find exactly what you’re looking for. A search for “meeting w/ the payments company” will find “Stripe Call — January 17, 2022” even without any of those keywords appearing in the mem itself.

Intelligent tagging, suggested bundling of mems, automatic information routing within teams, and much more are all on the horizon. You can sign up for early access to the Mem X plan or learn more at mem.ai/x.

Mem X Team & Enterprise Plans

Mem X unlocks extraordinary creative and intellectual power for individuals. For teams and companies on Mem X, the transformation is even more profound.

When a group of people use Mem X together, they don’t have to agree on where to put files and how to tag items. They can simply write and share knowledge freely, and let Mem X handle the rest. Mem X Teams and Mem X Enterprise unlocks true collective intelligence.

Similar Mems shows mems written by anyone across the team that are relevant to the mem you’re working on. This enables you to build off of prior art you may not have even known existed.

In a team setting, the person searching for information often has no idea what keywords may appear in what they’re trying to find — because they didn’t create it in the first place. With Smart Search, team members can search with queries like “how we think about pricing” and instantly find the “Monetization Strategy” mem.

The Mem X Teams plan, priced at $15 per user per month, is perfect for small-to-medium sized teams. Sign up for early access to Mem X Teams.

For larger teams and companies with custom needs, we’re introducing Mem X Enterprise. Contact us if you’re interested in getting your company early access to Mem X.

Originally posted to the Memo on August 16, 2021.

By Priscilla Mok

A few little words. “Technical” and “non-technical”. They seem innocent enough, and pretty much standard parlance in Silicon Valley — such as “a startup looking for its first non-technical hire”. Yet as I’ve realized, these little words can have a big impact on an early-stage company looking to build an inclusive and high-performing culture.

During my seven years as a designer at Google, I was part of the Engineering organization which included engineers, designers, and product managers. (The other big part of Google was Sales/Global Business Operations.) Being in the engineering org felt normal to me. After all, I’d always considered myself “technical”: I’d taught myself to code in middle school (learning via Neopets), troubleshooted my parents’ computers, worked in specialized software like Figma, and collaborated with engineers every day. Belonging to the engineering org of a big tech company helped reinforce that self-identity.

So I would’ve thought nothing of those labels when I joined Mem, where the terms “technical” and “non-technical” were also used casually, in everyday chats and light jokes about how to split up into teams for a board game… except for the times when I was put in the “non-technical” bucket.

I’d feel a small jolt whenever that happened. Not necessarily because being labeled “non-technical” was bad or there was any malice behind it (although because of Google’s engineering-centric culture, I’d enjoyed some perks that made one bucket seem better than the other). I started paying attention because for the first time, the label was different from my own self-identity. My first thoughts were to prove to people that I was just in the “wrong” bucket. But then that got me thinking — what did these labels even mean? What was the point of using them? And more importantly, how might thinking about our teammates in this way affect Mem’s culture?

I talked through these thoughts with our founders, Kevin and Dennis, as well as others on the team, who were supportive and receptive. I did some more reading on the topic from others in tech who felt similar reservations about these labels. And as it turns out, little words can mean a lot. Little words can affect the way people view and treat each other, and themselves — everything from creating an unspoken social caste system where “technical” people’s time is prized over all others’, to preventing “non-technical” people from wanting to write and deploy code to production (e.g. making changes to the marketing site).

And so, drawing from our past experiences at other companies, and discussing more intentionally the type of culture we do want to foster at Mem, I worked with the team to draft up an internal memo for how we’d like every Memer to see themselves, and each other. We’re sharing this memo below, and hope it inspires you to reflect on the kind of default labels and categories that might exist in your own organization.

Everyone is a builder

At Mem, we value all the skills that a Memer brings to the table. As such, we don’t use the terms “non-technical” and “technical” to label people and functions.

At its core, “technical” oftentimes refers to a “technical skill that is an ability to perform certain specialized tasks within some domain”. Which means coding is definitely a technical skill, but so is running analyses using Mixpanel, interviewing customers, writing/producing content to explain how to use Mem, or creating designs in Figma.

“Non-technical” skills often refer to “soft” skills such as communication, mentoring, conflict resolution and negotiation, diplomacy, and the like.

Over time, these terms have been co-opted by the tech industry to describe some roles (either strictly engineering roles, or ones that involve building the product like product management and design) as “technical”, whereas roles that did not contribute to building the actual product were “non-technical”. This has led to the terms also being used to commonly describe people and functions, such as a “startup looking for its first non-technical hire”.

However, there are subtle problems with using “technical” and “non-technical” to refer to people and functions that can cause unintended consequences for a company’s culture. Here are some examples:

— It can lead to misguided engineering elitism of companies over-valuing engineering and product, and people in “non-technical” roles feeling like second-class citizens (e.g. outsized recognition for the engineer(s) who build and ship a feature, free lunches for engineers but not sales in some companies)

— Labeling someone as non-technical can discourage them from learning technical skills and contributing in new and creative ways to the company. At worst, it can create a self-limiting identity that creates a fixed mindset over a growth mindset. In 2021, anyone performing almost any role inside of a technology company can benefit from an understanding of code, and at Mem, we encourage anyone who wants to learn, to learn! (The converse is true: an engineer who’s always been given feedback that they are “technical”, even in a positive way, may feel like they would never be a good people manager or a captivating presenter.)

— It can perpetuate a misunderstanding of other functions (e.g. marketing, data analysis, design) entail that just happen to not involve writing production code

— It can create bias in the hiring process — describing someone as “not technical enough” is an easy and vague way out versus saying “the candidate had great communication skills but we would’ve liked to see more proficiency in TypeScript”.Instead of saying that a candidate was “not technical”, we just describe what skill it was that they were lacking in

In other words, we believe that while skills can be described as technical or non-technical, people shouldn’t be.

At Mem, we set a high hiring bar in both technical and non-technical skills and believe both are important to build a healthy, diverse company. We value people who are always looking to grow and improve, in both of those skill sets. We believe that everyone who joins should be proud of their role and that everyone has important contributions to make to Mem — whether that’s coming up with creative ways to engage our community, shipping features, or cooking up the next great Tweet storm. For many of us, we do all of the above.

So instead of thinking of people in terms of “technical” or “non-technical”, at Mem we’d like to think that everyone is a builder. It doesn’t matter whether you’re building up the codebase, the design system, relationships with our customers, or more efficient processes. While we may still use “technical” and “non-technical” to describe skill sets out of convenience, when it comes to your role and contributions, the sky’s the limit.

Further reading

And many thanks to Jennifer Kim, April Wensel, and Dawn Parzych for their writing that helped inform this memo.

https://inside.lever.co/why-you-shouldnt-label-team-members-as-technical-or-nontechnical-47020f5527d7

https://aprilwensel.medium.com/if-you-can-use-a-fork-youre-technical-352e21d92c87

https://opensource.com/article/21/2/what-technical

Originally posted to the Memo on June 10, 2021.

By Scott Mackie

Since our beginnings in 2019, we’ve visualized the long-term model of Mem as a bowtie.

On the left side of the bowtie, you have a variety of inputs of information. They could be text messages, sound clips, videos, emails, documents, calendar events — you name it. We call these inflows.

Next, they all funnel into the center of the bowtie: the place where your information is connected, contextualized, and automatically structured to become your very own intelligent, assistive database. This is your Mem knowledge graph.

Finally, out the right side of the the bowtie comes structured knowledge that can be used to power other products and experiences you use. For example, the tasks in your knowledge graph will be syncable to your favorite task manager, the companies and clients you’ve met with will appear in your CRM, the movies recommended to you by your friend will power your streaming service. These are the outflows.

We knew; however, that critical to this picture was ensuring there was a defaultway for people to quickly capture new inputs of unstructured information into their Mem or effortlessly search across their own knowledge.

So, we started by building what is today the Mem beta app: lightning-fast capture, instant search, and suggestions of relevant knowledge everywhere. In a sense, quick capture and search, both available through Mem Spotlight or the core Mem app, became the first inflows and outflows to the Mem bowtie.

Soon after, we introduced a few other inflows: Texts — which let you use text SMS, WhatsApp, or Telegram to add text snippets into your Mem — and Calendar — which syncs a Google Calendar into your Mem, powering automatic organization of content and workflows around individual and recurring meetings.

Today, we’re opening the doors to the Mem bowtie: starting with an API that enables anyone to build new inflows.

Zooming into the knowledge graph

When we think about the Mem knowledge graph — the center of the bowtie described above — it’s useful to consider what types of information might be stored inside.

Let’s say each node in the Mem knowledge graph is an “entity”. An entity could be a mem (the flexible text-based containers for information that we have in the Mem app today). But an entity could also be a more specific, tangible concept. An entity could represent a specific calendar event, a person you know, a task you need to complete, a restaurant you want to try, an address of a friend you plan to visit — the list goes on.

Over time, Mem knowledge graph will automatically extract entities out of other entities to generate new knowledge. Imagine you write down a quick mem mentioning that a friend recommended a restaurant to you. Both the friend and the restaurant will then be automatically understood and represented as unique entities, and a relationship between them will be automatically formed. Their existence can power any outflow that depends on the set of restaurants you care about or your contacts list.

Today, the Mem API will only support the creation of the “mem” entity type — a flexible text-based container of information. But what this implies for the Mem API is that — over time — we will open the door for developers to build inflows that push any entity type into your Mem. This will enable developers to automatically sync a person’s contacts into their Mem, all of the structured tasks from other productivity tools that already exists, individual calendar events, and ultimately, custom entity types so that developers can model any type of record that would be useful to power an individual’s or organization’s assistive, intelligent knowledge graph.

Crafting the developer experience

We’re on a mission to deliver a best-in-class developer experience.

We drew inspiration for best practices across some of the most beloved APIs and integration platforms such as Stripe, Slack, and Github. The surface area of the initial API is intentionally slim and approachable, yet powerful with the flexibility to grow. We went through multiple iterations before landing on an elegant solution that lets you create a mem with a single line of JavaScript code:

For authorization, we’re starting with the simplest setup possible: API keys. You’ll be able to generate a new API key for each new Mem inflow you want to build or use, and simply plug and play to get started.

The other side of the developer experience is distribution. We’re committed to helping developers who build on top of Mem reach their intended audience — through the Mem Flow Store. We’ve been carefully working through the developer and end-user experience of what will ultimately become a marketplace of applications built on top of the Mem knowledge graph. In the near future, developers will be able to integrate with the Mem API through OAuth instead of API keys and publish the inflows and outflows they develop directly to the Flow Store — available for other users of Mem to install.

What you can build starting today

We’re excited to see what inflows begin to get built on the Mem API. To get the ideas flowing, we’ve compiled some concepts we know the Mem community would be eager to try.

They fall roughly into three categories:

• One-time import flows — e.g. From Evernote, From Markdown files, From Google Docs, From Notion, From Confluence

• Continuous, passive sync flows — e.g. Your bike rides from Strava, Your favorited recipes from AllRecipes‍

• Active inflows — e.g. Email into Mem, Readwise into Mem, Slack into Mem‍

Moving forward

This is just the beginning for the Mem API. Over time, three main areas will continue to mature:

• Inflow APIs — We will launch API endpoints that allow creation of new entity types that go far beyond the markdown-based mem format. We envision enabling the flow of structured knowledge, such as a contacts list, companies, tasks, and even custom records, directly into a Mem knowledge graph.‍

• Outflow APIs — We will launch API endpoints that integrations that read from a Mem knowledge graph and use that to power other products. We envision enabling use cases like syncing your tasks outbound to a product like Todoist; syncing contacts, companies, and mems to your system of record such as Salesforce or Airtable; or something as out there as building an entirely new UX atop your Mem.‍

• Distribution of integrations — We will launch the Mem Flow Store, enabling developers to distribute what they build directly to people using Mem so they can effortlessly connect new inflows and outflows to their own accounts.

Get started right now

So much of the information we end up searching for is information that we’ve come across before, but at that time didn’t realize we may need to reference again. That’s why it’s so important to not only be able to capture thing you explicitly want to remember, but also passively accumulate information and knowledge in the background that can be automatically used to power your needs down the road.

We can’t wait to see what you build atop the Mem API.‍

Get started with the API by heading to https://docs.mem.ai, and tweet us at @memdotai to share your ideas, progress toward building your first inflow, or feedback on the future of the API.

Originally posted to the Memo on May 3, 2021.

By Dennis Xu

Since the beginning of February, after we started to regularly invite people off the waitlist, we’ve seen an overwhelming amount of support, feedback, and suggestions from the burgeoning Mem community. As an early beta user, you are the lifeblood of what we are building — thank you for being a part of this journey.

We want to shed some insight into what we are (and are not) prioritizing, so that you can get a sense of how Mem will evolve into the future. Our hope is that by clearly communicating our intentions, we will give you the information you need to decide whether or not Mem is a product you want to invest in today and into the future.

What we are prioritizing

‍Information Flow & Data Portability
Move information to and from the right places‍

We’re building towards a world where every user of Mem has a secure and portable memory that they can capture to and access from anywhere. The information you store inside of Mem should be accessible inside of whatever context you might be in. This is why Mem Spotlight has been, and will continue to be, one of our most heavily prioritized product surfaces.

This is also why we are releasing our first foray into mobile (iOS) later this summer. If you want to be included in the TestFlight, sign up here.

But Spotlight and Mobile are just the tips of the iceberg. Our aspiration is to make information platform agnostic. Knowledge should not be trapped inside of the interface it was captured inside of.

Towards this vision, we’re releasing the first version of the Mem API in May (if you’re a developer, sign up here for early access). This will be a small but important step (initially allowing you to programmatically create mems) towards making your information universally accessible.‍

Intelligence
Automatically derive value from what you capture‍

Mem was founded on the belief that we should exert increasingly less effort to make sense of the information around us.

What was the link that Jane shared during our meeting last week? What about the name of the FinTech company that I’m meeting tomorrow? Who are they connected to that I know?

In a world where we can find publicly accessible knowledge in the blink of an eye, it’s still nearly impossible to access information that is uniquely relevant to ourselves. What would it mean to bring the power of Google to your personal knowledge?

We’re building the most advanced knowledge graph in the world (the Mem Graph) for your personal (and team’s) information. Mem Graph will be able to handle semantic intents and further extend Mem’s ability to automatically organize information on your behalf.

We are committed to putting the “ai” in mem.ai.

‍Data Ownership
You own your data‍

Neither Facebook nor Google should own your data — you should.

Having ownership over your data requires that you have both access and control.

To have access is to know what the Mem knows. For example, we aggregate all of the tasks that you capture inside of Mem. Today, we show you this via our Tasks View. But what if the view we chose to build isn’t your ideal way of managing tasks? What if there is another app, focusing exclusively on tasks, that caters to your preferences better than we can? Every other product that exists today requires you to conform your behavior to their opinions. We believe this is wrong — your data should not be trapped inside of the interface it’s captured inside of. Future versions of the API will expose Mem Graph’s understanding of what you capture directly to you. Eventually, you will even be able to use natural language queries (e.g. “all of the tasks I created last week”) to recall and manipulate your information.

To have control is to have the power to decide who can access your data, and what they can use it for. Rather than solving the hard problem of maintaining both privacy and portability, most companies today sacrifice one for the other. The canonical solution to keeping your data private and secure has been to allow no one access to your data (e.g. offline-only, end-to-end encryption). The canonical solution to data portability (e.g. Facebook, Google) has been to allow anyone with deep enough pockets access to your data.

We believe it is neither necessary nor desirable to live in a world where consumers and businesses must choose between privacy and portability. We are committed to solutions that place data ownership back into your hands.

What we are not (currently) prioritizing

Formatting Customizability‍

Features like ability to highlight text, change text colors, and the ability to customize every keyboard shortcut to your hearts desires are not currently top-of-mind. We are prioritizing features that help you capture data in new ways (e.g. Tables) over those whose primary purpose is to help you craft a more beautiful document.
Dark Mode & other aesthetic improvements‍

There’s a joke that companies who run out of ideas start to run A/B tests and implement dark mode. While design is core to our values, we believe form follows function. Our foremost priority is in helping you do more with your information.

That being said, mobile will launch in Dark Mode first.

End-to-end encryption‍

Mem is not end-to-end encrypted, and it won’t be for the foreseeable future. This is because our core focus — our raison d’être — is to provide you with intelligence on top of your Mem (see the Intelligence section), and while there are ongoing research efforts towards enabling machine learning/NLP on encrypted data, these techniques have yet to reach the level of feasibility required for commercial applications.

We take your privacy seriously, and don’t believe that a lack of end-to-end encryption must mean a lack of privacy. To that end, we encrypt your data in transit with TLS and at rest with AES-256. We don’t sell your data. We don’t mine it to serve ads (and we never will).

We are in the midst of some of the most exciting times for converting state-of-the-art NLP research into practical applications. The people and companies who use Mem are those who want to leverage these new advances to power their lives and their work.