Get the latest tech news

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 behavior, but restrictions on access and disclosure raise questions about their independence.

None

Get the Android app

Or read this on TechCrunch

Read more on:

Photo of OpenAI

OpenAI

Photo of Apollo

Apollo

Photo of AI subversion

AI subversion

Related news:

News photo

Why a former OpenAI alumnus is building Mac data centres for AI agents

News photo

Why did some Apollo missions carry a grenade launcher? (2019)

News photo

OpenAI loses appeal to dismiss major copyright lawsuit by Toronto Star, other media