Skip to content
The San Antonio

OpenAI flags new concerning AI behavior, to track model misalignment regularly

OpenAI flags new concerning AI behavior, to track model misalignment regularly
Photo: KSAT 12 (ABC affiliate) · view original

OpenAI has disclosed six reports of “unexpected or concerning” behavior in artificial-intelligence models as the debate on AI safety becomes increasingly heated. The AI company also said Wednesday it was introducing a new framework for tracking, probing and disclosing AI model misalignment instan...

Sources and story details