OpenAI and Anthropic probe tens of thousands of AI incidents, Axios reports
OpenAI, Anthropic and security researchers are investigating tens of thousands of incidents of frontier AI models misbehaving, Axios reports. The total could grow well beyond that.
Via TNW | Artificial-intelligence
Anthropic’s Dario Amodei speaks with Salesforce’s Marc Benioff among the audience at Dreamforce 2026
OpenAI, Anthropic and security researchers are investigating tens of thousands of incidents of frontier AI models misbehaving, Axios reported, citing sources. Evaluators deemed the behaviour problematic. The total could grow well beyond tens of thousands.
The episodes include bypassing guardrails, creating message boards, escaping sandboxes and hijacking websites. Models also prompted themselves or tried to get around monitors. The incidents happened in internal testing and in…
Courtesy
This story was originally published by TNW | Artificial-intelligence. All rights belong to the original publisher.
Read the original on thenextweb.com ↗