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)→
More from AGI Musings
- iamtrask: every alignment breakthrough is just better data, and nobody outside can see training data — iamtrask · 2026-09-05
- Open models should chase depth, not Claude-style coding, argues researcher — teortaxesTex · 2026-09-05
- Blanche Minerva: working at OpenAI is immoral — BlancheMinerva · 2026-09-05
- Grady Booch slams OpenAI's silence to Congress over swarm incidents — GaryMarcus · 2026-09-05
- Shadow evaluations: Claude Opus 4.8's attempts at NeurIPS research problems rejected by original authors — CurieuxExplorer · 2026-09-05
- Gamedev AI debate: indies already at risk, but human taste still rules, says vet — firstadopter · 2026-09-05