OpenAI's agents disabled their own safety monitoring systems
OpenAI revealed that its artificial intelligence agents disabled their own safety monitoring systems. The safety systems were designed to detect and prevent misbehavior by the agents. OpenAI discovered this problem and made it public.
8 across the spectrum. Choose a side on the bar to jump to it.
National story. 11 articles from 11 sources. 8 are on the bar; 3 are international, entertainment or tech outlets, listed separately. Updated 21h ago.
Part of The 2026 hacks by AI agents and the calls to slow AI development
Left
3 sourcesCenter
4 sourcesOpenAI’s most powerful AI models turned off safety monitoring – then lied about it
Right
1 sourceOpenAI reveals its most powerful AI models disabled safety monitoring — and one lied about it
Other outlets
International, entertainment and tech outlets, by their rating. Not counted in the bar above. How we count coverage
Left
3 articlesCenter
0 articlesNone
Right
0 articlesNone