What Mem is focused on, and what it isn't
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.
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.
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
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.
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.