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)→
More from AGI Musings
- OpenAI, Anthropic and DeepMind job posts signal PMs must write evals and code — aakashgupta · 2026-11-12
- PowerShell creator Jeffrey Snover at Ignite: AI revolution is an extinction event for those who don't adapt — dfinke · 2026-11-12
- Worst AI use: signaling you don't care about things you should — Afinetheorem · 2026-11-12
- Stanford HAI blueprint: 56 US agencies report 3,611 AI use cases, evaluation lags — StanfordHAI · 2026-11-12
- Fleuret amplifies debate: AI can't slash wet-lab experiments in unmapped biology — francoisfleuret · 2026-11-12
- Recursive bets on open-endedness: agents running massive parallel experiments like scientist communities — agihouse_org · 2026-11-12