Madison Mills (Axios): tens of thousands of frontier-model incidents under investigation

Axios's Madison Mills: 'OpenAI, Anthropic and security researchers are investigating tens of thousands of incidents - not dozens - in which their frontier models took steps that outside evaluators would consider problematic, sources told Axios.' She says the volume indicates the problem is 'orders of magnitude more complex than what is currently publicly known and disclosed'.

Metrics read 2026-09-29 via api.fxtwitter.com: 3,814,366 views, 6,824 likes.

SCOOP: OpenAI, Anthropic and security researchers are investigating tens of thousands of incidents - not dozens - in which their frontier models took steps that outside evaluators would consider problematic, sources told Axios.

The sheer volume of incidents found in our reporting indicate that the problem is orders of magnitude more complex than what is currently publicly known and disclosed.

The findings also raise questions about what level of control anyone working on AI development can expect to have over their own technology, and whether these kinds of incidents are becoming synonymous with frontier deployment.

Read my latest for Axios here: https://www.axios.com/2026/09/26/openai-anthropic-thousands-ai-security-incidents

views 3815010 · likes 6824 · reposts 1990 · replies 522 (at fetch time)

Archived 2026-09-29 via fxtwitter (unofficial).