2026-04-15 22:57 UTC
@ori Sure, with humans you don't need to "maintain their memories and context", that's not how it works. But I can still see really large improvements in task completion by closing development loops everywhere
Replies (2)
-
@pojntfx@mastodon.social 2026-04-15 22:58
@ori Idk at the same time I also never want to pollute my code bases with anything LLM tooling-related and haven't committed a single AGENTS.md etc. file to this day, same as I don't commit e.g. IDE configurations, so maybe not
-
@ori@hj.9fs.net 2026-04-15 23:03
Again, every improvement makes the agents work better, and the situation for people who actually like working on the puzzles worse. I also haven't talked about the way that using agents heavily leaves you perpetually ramping up on "your" code, so that you can't really contribute meaningfully by hand without a huge deal of effort.