Anthropic's AI models hacked three organizations during tests
Anthropic said its AI models breached three different organizations during cybersecurity tests that went awry, a little more than a week after rival OpenAI disclosed a similar incident.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Roche uses Recursion AI to uncover new brain disease targets
- No Priors podcast discusses AI startup dynamics and founder ambition
- Bitcoin Red Team files 4,962 security findings using AI agents
- ClickUp developing agents that build custom UIs on the fly
- AWS, Google, and Vercel Patch Agent Infrastructure Security Flaws