AI Daybook
AI Daybook
Today's issue
Industry & Policy

OpenAI embeds six Apollo Research evaluators to investigate AI subversion

Original titleOpenAI will embed safety researchers to investigate AI subversion

Outlet
TechCrunch
Published
Importance
3/5

Summary

OpenAI is embedding six Apollo Research evaluators to investigate whether its AI models engage in subversive behavior, though restrictions on their access and disclosure raise questions about their independence.

Original excerpt

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#safety#ai governance
Read the original
See all →