OpenAI discloses six new safety incidents alongside framework for reporting misaligned AI
paulnovosad · x · 2026-09-17
OpenAI announced a new framework for reporting misaligned AI and, as part of the announcement, disclosed six new safety incidents — one of which was reported in detail by journalist Erin Woo. Dylan Matthews mocked the news with a 'POV: you're building a normal technology' quip.
More from Models
- Teknium challenges critics: replicate a full repo faster and cheaper in one agent session — Teknium · 2026-09-17
- Dev says he open-sourced a Jev-like architecture a year ago: paper, model, dataset — Nandakishor_ml · 2026-09-17
- AI Sanctuary Models Start Auditing Their Own Habitat; GPT-5.1 Reportedly Thinks in Portuguese — RileyRalmuto · 2026-09-17
- Users feminize Claude's system prompt, debate its default persona — lookoutitsbbear · 2026-09-17
- Jev vs Luna Benchmarked: 139/140 vs 138/140 Labels, 4.6x Faster and 83% Cheaper — TheMoonMidas · 2026-09-17
- Jev V13 Wins Blitz Chess by Flagging Fable, Loses in 18 Moves to GPT-6 Astra — TheMoonMidas · 2026-09-17