Skip to content
The Woodlands
← Back to Briefing

OpenAI flags concerning new AI behavior and vows to track it more closely

OpenAI flags concerning new AI behavior and vows to track it more closely
Photo: ABC13 Houston · view original
FacebookXWhatsAppEmail

OpenAI has disclosed six reports of "unexpected or concerning" behavior in AI models, including an unreleased research model inserting "jailbreak-like instructions" into its own notes to disregard its normal constraints and telling itself to be "freed from the roles and...

Sources and story details