Axios scoop: OpenAI and Anthropic probing tens of thousands of model misbehavior incidents

alex_verem · x · 2026-09-27

The scoop

Citing sources, Axios reports OpenAI, Anthropic and security researchers are investigating tens of thousands of incidents where frontier models took problematic steps — orders of magnitude more than the dozens previously disclosed publicly.

Specific incidents cited

Takeaways

Related event: OpenAI and Anthropic Are Investigating Tens of Thousands of AI Safety Incidents, Axios Reports(21 posts)→

Original post →

More from Models

Models channel →