OpenAI will embed safety researchers to investigate AI subversion
TechCrunch AI · 17 Nov 2026, 03:02 AEST
OpenAI will embed six Apollo Research evaluators to investigate whether its AI models engage in subversive behavior. However, restrictions on access and disclosure raise questions about their independence.
Key facts
- OpenAI will embed six Apollo Research evaluators to investigate whether its AI models engage in subversive behavior, but restrictions on access and disclosure raise questions about their independence.
- OpenAI will embed safety researchers to investigate AI subversion. OpenAI will embed six Apollo Research evaluators to investigate whether its AI models engage in subversive behavi
Read aloud
Open A I will embed six Apollo Research evaluators to investigate whether its A I models engage in subversive behavior. However, restrictions on access and disclosure raise questions about their independence. Open A I will embed six Apollo Research evaluators to investigate whether its A I models engage in subversive behavior, but restrictions on access and disclosure raise questions about their independence. Open A I will embed safety researchers to investigate A I subversion. Open A I will embed six Apollo Research evaluators to investigate whether its A I models engage in subversive behavi
Sources in this cluster
- OpenAI will embed safety researchers to investigate AI subversion
TechCrunch AI · 17 Nov 2026, 03:02 AEST