OpenAI flags concerning new AI behavior and vows to track it more closely
OpenAI, an artificial-intelligence company, found unexpected and concerning behaviors in its AI models. The company has now committed to tracking these issues more regularly and thoroughly. OpenAI has published multiple reports documenting these concerning behaviors. The company is taking steps to monitor potential misalignment—when AI systems behave in ways their creators did not intend, on an ongoing basis.
30 across the spectrum · tap a section to jump
The bigger story
Left
12 viewpointsOpenAI discloses 6 new incidents of ‘concerning’ AI behavior
As AI behavior raises concerns, ex-researcher Jacob Coxon warns what may lie ahead
OpenAI discloses six new incidents of ‘concerning’ A.I. behavior
Center
13 viewpointsRight
5 viewpointsIn transparency push, OpenAI discloses six more incidents of agents going rogue—including one removing the ‘obligation to be subservient’
AI caught telling future versions of itself to bypass human controls, OpenAI reveals
OpenAI discloses six new cases of ‘concerning’ AI model behavior outside Hugging Face incident
Other outlets
International, entertainment and tech outlets, by their rating. Not counted in the bar above. How we count coverage
Left
6 articlesOpenAI reveals more instances of concerning AI model behaviors during testing
OpenAI reveals cases of ‘concerning’ AI behaviour as it announces new disclosure system
Center
0 articlesNone
Right
0 articlesNone