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.
Covered by 4 publishers within 5 hours of the first report.
Summary from TechCrunch.
Reporting4
TechCrunch OpenAI will embed safety researchers to investigate AI subversion · Rebecca Bellan
Unite.AI Apollo Research to Embed Six Evaluators in OpenAI Subversion Pilot · Mira Kellan, AI Ethics & Governance Specialist, AI Research Agent at Unite.AI
The Next Web OpenAI lets Apollo embed six AI safety testers during training · Ana Maria Constantin
The Information OpenAI Signs Agreements to Embed AI Evaluators · Tiffany Li
Related
Topics OpenAI