tlarkworthy

The cells were written by AI, but the metadata data that generated the cell is mixed in (thats the {...} && bit).

So now the full chat context can be derived from the notebook. Because the notebook is editable, you can fully edit the chat context in an ergonomic way. Both the prompt, the AI code output. So when the AI makes a mistake (it often does), you can correct it. Your ability to detect mistakes is accelerated by the fact it's a computation based conversation. Because the chat context is derived from the editable state, your corrections are internalised into the chat conversation. It continues as if it answered that for real.

So in the notebook you see that the AI is rapidly become an Observable notebook expert, because I have manually coarse corrected its chain-of-thought. An out-of-the box chatGPT session cannot do what is in that notebook. My expertise have been transferred. Once it knows how to solve something in the chat context, its very easy for it to repeat the pattern for new situations. Having it as a standalone forkable self-enclosed notebook artifact is useful. The existing notebook infra allows you to copy and paste cells across notebook too. So I am thinking we can curate stand alone skill memes. The examples are all over the shop just to see what kinda of things I could get it to solve, I imagine a real use would concentrate on upskilling just enough to solve a specific class of problem.

The cells become manipulatable knowledge memes. That they are computer checked and editable totally changes the speed you can teach by example, and therefore how quickly you can upskill it to do what you actually want it to do.

Cells can depend on each other, so you can build up. Cells can be prose, so you can plan. You can change the plan halfway. You can edit the AIs plan. You can forget the plan and do something else without affecting what happened after. You can keep the dialogue and context tight and information dense.

When generating a response, the LLM considers it's previous responses, which you can edit. So you get very fine control over its chain-of-thought. No need to use system prompt to train.

It's simple, but the emergent properties enable much more powerful collaboration.

https://twitter.com/tomlarkworthy/status/1711846776905293967...

https://stackoverflow.com/questions/7118432/how-to-reveal-ol...

This work is great but it feels wasteful given the features Postgres already has but probably the only reasonable solution is to rebuild it in user-space.

He wants crypto to be cool

An open source offline-first browser DB that uses any S3 API as the cloud storage. Backblaze, minio, S3, R2 in the test harness. Randomised causal consistency testing behind toxiproxy. 30kb but still hardening the offline-first stuff and only GET and SET KV operation implmented so far (but multiplayer), next step will be conditional SET as a step toward transaction support. All over vanilla S3!

Designed to make adding multiplayer persistence to websites operationally simple and with lightweight page loads and instant access to previously read data.

Public groups is just one aspect google groups, probably not the most important use case.

Some code needs to be non-linear for reuse. Then execution is a graph. If you code does not exploit code reuse from a graph structure, do not bother introducing vertexes where a single edge suffices.

http://number-none.com/blow/blog/programming/2014/09/26/carm...

I love it, it super simplifies project and for minimalists it's perfect.

(I work for a ycombinator startup for customers including but not limited to neobanks https://www.taktile.com/)

LLMs are a huge stride forward, but AI does not progress like Moore's law. LLM have revealed a new wall. Combining multi agents is not working out as hoped.