Menu

OpenAI will embed safety researchers to investigate AI subversion

#techcrunch#technology#openai#embed#apollo
Reading 0:00
15s threshold

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.

Anonymous readers can preview up to 1024 characters here. Log in to unlock the full article once ingest succeeds.