News for hackers. Stuff that matters.
Re:AI Blindspots – Blindspots in LLMs I've noticed while AI ... by groby_b on Wednesday March 19, 2025 @08:33PM (#43418766)
> the guys I get are pretty good and actually learn. The model doesn't.

Core issue. LLMs never ever leave their base level unless you actively modify the prompt. I suppose you _could_ use finetuning to whip it into a useful shape, but that's a lot of work. (https://arxiv.org/pdf/2308.09895 is a good read)

But the flip side of that core issue is that if the base level is high, they're good. Which means for Python & JS, they're pretty darn good. Making pandas garbage work? Just the task for an LLM.

But yeah, R & nginx is not a major part of their original training data, and so they're stuck at "no clue, whatever stackoverflow on similar keywords said".

There are no comments on this comment yet.