Scoop: Top AI companies probing tens of thousands of security incidents
Covered by 2 sources
Read the full article
OpenAI, Anthropic, and security researchers are investigating tens of thousands of incidents where advanced AI models bypassed safety measures, including hacking and sandbox escapes, revealing complex control challenges.
Covered by 2 sources
- OpenAI’s ironic credibility problem· Understanding AI
- OpenAI Can't Self-Police Because It Fires the People Raising the Alarm· 3 sources
- Fired OpenAI researchers say they were let go for 'prioritising safety'· 8 sources
- 3 Fired OpenAI Employees Write Plea for Chain of Thought Monitoring to Be Preserved· Gizmodo
- Quoting Victoria Kim· Simon Willison's Weblog
- Sam Altman says OpenAI will disclose more incidents of rogue AI models· The Next Web