@lilacperegrine@clockwork.monster
Post #1490158
2026-02-26 14:09 UTC
@ngaylinn
i mean there is a large disconnect with how effective coding assistants are and how effective they *feel*.
LLMs appear to be at least a half-decent approximation of the left half of the brain, "hallucinations" and all
but humans seem to have that damped down internally - as in internal mechanisms make some of those weird ideas go away
LLMs/"agents" have no real internal state than be used as a fallback
there is the system prompt - but that can be overwhelmed as the model continues
Replies (1)
-
@lilacperegrine@clockwork.monster 2026-02-26 14:12
@ngaylinn but for "agents", they just use more language as the internal regulating mechanism. If you assume philosophy is a game played with language, then LLMs would be approximating thought, but that's a hell of an assumption.