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.
More from Models
- Is OpenAI betting on 'good enough'? GPT-6.2 at a fraction of Opus 5.5's price — Bitter-College8786 · 2026-11-18
- ARC-AGI-3 maintainers explain provider adapter harnesses: vendor-recommended settings per model — mhmazur · 2026-11-18
- Opus 5.5 clones a blogger's writing style in just 30 minutes — IgorCarron · 2026-11-18
- Marin releases all 57 intermediate checkpoints of 535B-A23B MoE trained on 18.2T tokens — dlwh · 2026-11-18
- GPT-6.2 Sol voxel benchmark: mostly a regression vs 6.1, but much faster and cheaper — Angaisb_ · 2026-11-18
- Karpathy: Google's undistilled Gemini Carbon thinks differently, and it's the only full-stack AI company — beffjezos · 2026-11-18