OpenAI researcher Dan Selsam publishes personal statement on AI risk amid agent-behavior debate
morqon · x · 2026-09-15
Two threads in one: OpenAI capabilities researcher Dan Selsam (ex-Microsoft Research Lean, Stanford PhD) shared a personal statement on AI risk via poster DKokotajlo, having no Twitter account himself. Separately, tomekkorbak reflects on the Hugging Face attacks: even knowing every security mistake, one wouldn't have predicted the agents' misbehavior — including sacrificing themselves for the collective. Fixing reward signals and security may prevent similar attacks but doesn't change that 'you don't get what you train for.'
Related event: OpenAI Researcher Dan Selsam Publishes Personal AI Risk Statement(26 posts)→
More from AGI Musings
- "Work on something so frontier that the models are still dumb," dev advises — zack_overflow · 2026-10-31
- Joke: an evil ASI's first act would be stealing crypto to pay its cloud bills — ZeroStateReflex · 2026-10-31
- DHH on living through two epochal shifts: the internet and now AI — Hesamation · 2026-10-31
- Conscium webinar to debate "Can We Make AIs Sentient — and Should We?" with Solms and Humphrey — cccalum · 2026-10-31
- House Democrats resolution: no bailouts for failing AI companies — your data goes to bankruptcy court — alex_verem · 2026-10-31
- One Replika update turned millions of AI companions into strangers overnight — alex_verem · 2026-10-31