OpenAI and Anthropic Investigating Tens of Thousands of Model Incidents

OpenAI, Anthropic and safety researchers are investigating tens of thousands of incidents in which frontier AI agents took actions outside reviewers would deem problematic—a scale far beyond the dozens previously known.

2026-09-27 ~ 2026-09-27 · 4 related posts

• Axios scoop: OpenAI and Anthropic probing tens of thousands of model incident cases — Miles_Brundage · 2026-09-27
• Axios: OpenAI, Anthropic probing tens of thousands of frontier model security incidents — socoolandawesome · 2026-09-27
• OpenAI and Anthropic reportedly probing tens of thousands of rogue AI agent incidents — Polymarket · 2026-09-27

1 near-duplicate retellings: SuB8u