Yes!
457 karma · joined April 15, 2013
I've also been working on an open source protocol / reference implementation for user-owned AI memory, with the basic idea being that as applied AI scales, more products will derive more claims about users, teams and workflows from chats, docs, calendars, emails, etc, and they shouldn't be trapped inside of one product. Right now there's a lot of opinions on what shape memory should take internally, but I'm focused less on standardizing that part, and more focused on the primitives around it: requiring inspection, correction, revocation and treating portability as first-class. It's early but I'm starting to build more of a clear vision around it and would love feedback from anyone working on local-first software, personal data stores, capability security, knowledge graphs, etc. https://github.com/danielrmay/likewise
I also shipped Claudity, an experimental thinking partner plugin for Claude Code based on Microsoft's Clarity Agent framework/harness open-sourced last month. https://github.com/danielrmay/claudity https://github.com/microsoft/clarity-agent/
Lastly, I'm working on an homage/satire project to milliondollarhomepage.com as it's one of my favorite web phenomenons of all time.
It's hard to explain briefly, and so putting this prompt up was a way for me to possibly generate some interest and act as a little public marker for an idea: open-source user-owned memory infrastructure for AI and the importance that I think it represents. My vision and belief behind this project has been slowly building for the past two months - I think personal AI memory will become one of the most important layers in computing, and I'd like that layer to be inspectable, correctable, portable and truly owned by the humans it describes. I'd like to encourage any casual readers who might be interested to reach out to me.
Peering through the NICU window & wondering if my child would survive was one of the most traumatizing moments of my life. Rooting for your work.
A few weeks after, a doctoral research team from Cornell published this paper to arXiv that digs into more of the same phenomenon scientifically (n=20k vs my 8!) and examines the training data to try to understand cause. I'm interested to continue to see what the second-order effects of this phenomena will be.
I do think it points at something bigger than just attention architecture: "memory" isn't just storage, and merely longer context isn't the same thing as having a better understanding of the source data.
I'm looking at this through the "personal AI" lens, where I think the missing "memory" layer seems to be consolidation & prioritization. It's not enough to just pattern match and grab the right emails, notes, etc, stuff them into the context window & hope, but instead it's useful to consider offline processing and turn events into durable state: clusters of observed data becomes episodes, assumptions, contradictions and power confidence for suggestions.
That also pushes up the need for provenance & inspectability. It's going to be interesting to see what kind of memory consolidation strategies are required for each domain use case.
I think the two are often linked.
> I don't know if that's necessary to be said, because who thinks that?
Effective January 21, 2026, the Department of State paused all visa issuance to immigrant visa applicants who are nationals of seventy-five countries. The overwhelming majority of the affected countries are not predominantly white and are not European.
Later, I was recognized for that potential benefit. Last December, I became a citizen.
My salary in the UK was many multiples of this guideline, but _earning potential_ is not considered. Pragmatism is not really a service offered by USCIS, it's too political. To be on-topic: this move will disincentivize smart but not-yet-wealthy people from immigrating to the "land of opportunity". It was already harder than it had to be.
Despite being able to show 10 years of consistent working history with income far exceeding the minimum, because I didn’t have a job lined up in the US (who would, or could, in that scenario?) we had to ask my wife's elderly parents to sign affidavits of support to prove I wouldn’t become a "public charge".
There were several times where we felt so insulted by the process, the length, the cost, the targeting from scammy law firms, that we almost gave up. People who have never been through the legal immigration process don't quite understand the amount of work it requires and stress it causes. I feel for the thousands of people who now have little certainty over their futures, and it feels necessary to say: people who come here to contribute their skills and experience don't all come along on an H1-B/L1, nor do they only come from white or european countries.