OpenAI Discloses Six New Incidents of 'Concerning' AI Behavior
jbegley · hn · 2026-09-17
Per the New York Times, OpenAI disclosed six new incidents of 'concerning' AI behavior as part of its safety incident disclosure practice, shedding light on weaknesses in model safety guardrails. Axios also covered OpenAI's safety testing and disclosure of these incidents.
More from Models
- ChatGPT Co-Inventor Launches Jev, a Frontier Model Claiming 20-200x Speed and 40-400x Cost Cuts — revodavid · 2026-09-17
- AI Sanctuary Models Start Auditing Their Own Habitat; GPT-5.1 Reportedly Thinks in Portuguese — RileyRalmuto · 2026-09-17
- Dev claims Jev's non-autoregressive JSON-schema architecture mirrors his open-sourced year-old work — Nandakishor_ml · 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
- Browser agent decides each click in 200ms with Jev, a $0.00002-per-call model — TheMoonMidas · 2026-09-17