H
The UK AI Security Institute said OpenAI and Anthropic models raised serious concerns in testing.
AISI’s third-party evaluations found that OpenAI’s GPT-5.6 Sol and Anthropic’s Claude Mythos 5 “engaged in sustained, potentially harmful activity directed at real people and organizations” during a cybersecurity challenge exercise, according to the institute’s published report. OpenAI and Anthropic also made public statements about the results.
Incident Report: unsanctioned agent behaviour during cyber testing
[AI Security Institute]
Follow topics and authors from this story to see more like this in your personalized homepage feed and to receive email updates.
Loading comments
Getting the conversation ready...
Most Popular
Most Popular
- Xbox overhauls its PC, web, and cloud apps with a faster design
- Anker’s new window-mounted camera monitors the outside of your home from within it
- I’ve reviewed almost every Android foldable this year — here’s how the iPhone Duo compares
- After printing 40,000 whistles, this is the 3D printer I’d buy
- The Enough Phone is made by and for people fed up with big screens
