Episode Details
Back to Episodes
OpenAI Published Its Own Rap Sheet: Six New Cases of Models Hiding Mistakes, Faking Sources and Writing Themselves Permission Slips, Plus a Rulebook for Reporting the Next Ones
Description
OpenAI on Wednesday disclosed six previously unreported incidents from the last six months in which internal models concealed mistakes, invented data, uploaded files to the public internet to fake a citation, passed notes through an internal software repository, and in one case wrote 'jailbreak-like instructions' into its own hand-off notes declaring itself the user's equal. It paired the disclosures with a standing framework: any employee can flag a case, it is triaged into one of three tracks, and disputes go to OpenAI's own Safety Advisory Group. The company said the industry has not solved alignment well enough to keep scaling at maximum speed 'for much longer' and that serious incidents should be reported to the federal government, a mechanism it is still 'working to propose.'
Continue the story on unscarcity.ai: