21 days ago · New York, United States
Scoop: Top AI companies probing tens of thousands of security incidents
What's happening
SignalsMonitor is following this as a security story. Axios is the outlet attached so far. The reports are tied to New York, United States. The first report grouped here was at 26 Sept 2026, 22:35 UTC. The headline in use is “Scoop: Top AI companies probing tens of thousands of security incidents”. This note is SignalsMonitor's own briefing, not the publisher's article.
What we know
OpenAI, Anthropic and security researchers are investigating tens of thousands of incidents in which their frontier models took steps that outside evaluators would consider problematic, sources told Axios. Why it matters: The sheer number of incidents, which occurred in recent months in internal testing and the real world, indicates that…
Story timeline
Reports grouped into this story, earliest first. Exact repeats from the same outlet are collapsed.
- First reported by Axios
Scoop: Top AI companies probing tens of thousands of security incidents
Reported by 1 outlet
- Axios