Thinking about phenomenology - studying your own subjective experience of the world - and how it might relate to a world of super-capable AI. Meditation can be a way of doing it. read on scrawl

I read "Turning the database inside out" by Martin Kleppman. I've also been thinking about better ways of providing concise context for LLMs. Both have to do with stream processing. Especially struck by the Kleppman description of state made up of derived data from an append-only log of immutable facts. Which I think is also how people are starting to do memory for agents. read on scrawl

Working with embeddings - particularly with the goal of aiding thinking - a lot of the challenge is where do you draw the line for chunks. Paragraph-by-paragraph? Essay-length? Book-length? read on scrawl

I watched the Welch Labs video about the 'bitter lesson' and I think it shifted how I think about LLMs a bit. read on scrawl

I've been thinking about monks and tech and attention. If one of the challenges of life today is managing attention in a world of content designed to take it (ref Chris Hayes Sirens Call), then monks stand out as example of group that willingly placed constraints on their life in order to manage attention. read on scrawl

Thinking about personal OS. More like a personal dashboard but it could expand from there. read on scrawl

I was looking at a short school bus with three windows with three decals applied beneath. I think it was "Quality", "Bus", "Corp" or something like that. And I was looking to see how they had aligned the decals under the windows. Left-aligned on each one? Left, center, middle? read on scrawl

I want to try and sort / rearrange / explore some of my thoughts on why I make creative tools. read on scrawl

Looking at samplers and drum machine patterns and thinking about how their primitives map to other media. read on scrawl

I've been thinking about prediction. Mostly in the context of M being almost 2 years old and asking/demanding more things. read on scrawl

Morning 10 minute freewrite scrawl. I want to return to the timer concept today. Build out the frontend with the iframe portals. Reduce data scope down to just startTime, duration, and label (leave calendar time blocks for later). I think the shuffle mechanism will be the real small proof of what shared data/structure could do for generated apps. read on scrawl

I've been thinking about what makes an app or program feel coherent. Like they have an underlying logic. read on scrawl

read on scrawl

I think I pinpointed a misgiving I have about general collaborative LLM use: that the LLM will never stop and say "I don't know" or "I don't have this mental model, can you help me understand it". That's the fundamental limitation of being trained to plausibly (not correctly) generate text. read on scrawl

One of my favorite pieces of writing is The Web's Grain by Frank Chimero https://frankchimero.com/blog/2015/the-webs-grain/. Lately I've been trying to think about what the grain of LLM-related development could be. read on scrawl

I've been working on building rough shelves out of 2x4s in our basement. Partly for storage, partly to get more of a feel for how to frame things with 2x4s. The big improvement on the second set was using 3" deck screws. The process made me think about learning and how it feels different to have solved a problem versus avoiding having a problem. read on scrawl

I read (listened) to Nick Harkaway's Karla's Choice recently and then went back to the BBC audio versions of a bunch of the George Smiley novels. It's fascinating Harkaway can write Smiley so well when the tone of his own novels (which I also like) are so different. read on scrawl