Join Nostr
2026-08-29 17:07:10 UTC
in reply to

dan on Nostr: always. work. on. one. thing. at. a. time. llm by default will not do that, and in ...

always. work. on. one. thing. at. a. time.

llm by default will not do that, and in proof engineering doing >1 things at once gets you wrecked. it just can't make the right tradeoffs because it's trying to "finish" the proofs but what you want is an accurate model, not a typechecking wrong model