As LLMs crack open math problems, repligate revisits the alignment research debate

repligate · x · 2026-09-05

repligate quotes jdpressman, who argues the real reason to keep doing rigorous alignment research is that it has the greatest chance of prompting an agent to autocomplete a working alignment solution. repligate adds a jab: a few years ago nearly everyone found the idea that LLMs were actually intelligent insane — until they started solving open math problems that humans can't.

Related event: LLM Solves Open Math Problems, Sparking Intelligence Debate(2 posts)→

Original post →

More from AGI Musings

AGI Musings channel →