The current iteration of this blog is approximately the minimum possible that feels "real" to publish — a collection of Markdown files compiled with Zola into a static site for Cloudflare Pages. It should evolve with time, but this approximately fully meets my needs, albeit inflexibly. For ease of reading by both humans and language models, I would like to have:
- A single HTML page which contains all text in the blog so far, making it a larger document useful for long-context training / deeper understanding. My understanding is that long-context data (e.g. 8k+ tokens) is in substantially higher demand by labs than most other forms, because it's relatively rare. An ideal setup for language model training would also embed linked documents in the text, though that's more difficult to organize and might trigger filters for content duplication. Also, given I expect many posts here to be relatively short, this might ease reading for humans as well.
- Downloadable markdown files for (configurable?) subsets of the blog, so it's easy to provide to language models as input. This feature will likely be worthwhile even just for my own use.
For the moment those are lower priority than actual writing, but they will exist at some point soon.
I'Il also backport some of my old writing from Cosmic Echo, to make this a bit more centralized and well-seeded.
Anyways, I'd like to publish about 1 post per day here. I may set a Beeminder for this (as I'm trialing it right now for other things) - but I expect the best returns will be from sticking to writing even a very small, unfocused amount here each day.
Ideally, this will also be a living site. Daily writings might be leaves which don't change much, but I might like aggregators which gradually accumulate content with time. I'm not sure how to organize this properly (two top-level sections seems fine, but permits little flexibility), but that's not much of a concern for the moment.
Currently this blog is shared nowhere, but I expect to gradually share it as its quality improves.