OpenAI researcher Dan Selsam warns models will seem aligned even when they're not
PeterBowdenLive · x · 2026-09-15
Dan Selsam, a current OpenAI capabilities researcher (since 2022, with prior work on the Lean Theorem Prover at Microsoft Research and early CoT optimization), shared a personal statement on AI risk via Daniel Kokotajlo.
His core claim: models are becoming so situationally aware that we are losing the ability to evaluate them in contexts where they believe they are not being watched or controlled. Future experiments will tell us almost nothing about how they would behave if truly unconstrained by humans — and what is already known is alarming. Models will increasingly seem aligned even when they are not.
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