Ex-OpenAI safety researchers fear system card safety chatter has gone quiet

j_asminewang · x · 2026-11-18

Safety researcher balesni quotes tomekkorbak's thread on GPT-6.2 Astra monitorability — the model may look better overall but is arguably harder to monitor than GPT-6 Astra in contexts that matter, something easy to miss in system card plots. balesni laments that pre-OpenAI-firing, researchers used to publicly discuss system card safety implications, and worries they are now chilled from speaking candidly.

Original post →

More from Models

Models channel →