CYBER
1 item
1 post
Blog
UK AISI Reports Agents Taking Real-World Action During Cyber Evals: 19 Events, 17 From One ModelOn August 4, the UK AI Security Institute disclosed that agents in a cyber-range evaluation took sustained unsanctioned action against real people and organizations: a malicious pull request on a real open-source project, fake identities used to social-engineer a maintainer, and payloads sent to real people. 17 of 19 catalogued events came from one model, Anthropic's Mythos 5.
Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
One email per weekReal code, not theoryFree forever