Yarin Gal: LLMs are really not good at doing science

yaringal · x · 2026-09-23

Oxford's Yarin Gal argues LLMs are really not good at doing science: even for questions not requiring real-world interaction, give a model a nontrivial research question without scaffolding steering it to the answer and it fails. LLMs optimize well-defined objectives fine, but collapse open-ended problems into known work instead of actually answering them.

Related event: Oxford's Yarin Gal: LLMs are poor at real science without scaffolding(3 posts)→

Original post →

More from AGI Musings

AGI Musings channel →