Model Behavior - Search News

OpenAI, model misalignment

OpenAI reports 6 new instances of 'concerning model behavior' since March

OpenAI has disclosed six new cases of model misbehavior and offered a framework for disclosing future instances, as the debate over AI model safety intensifies.

· 1d · on MSN

OpenAI reports more concerning AI model behavior

· 1d · on MSN

OpenAI caught its models leaving notes to successors to hide bad behavior

· 1d

OpenAI flags new concerning behavior incidents and launches safety framework

OpenAI discloses six new concerning behavior incidents, prompting the launch of its new misalignment tracking framework.

· 1d

OpenAI reveals rogue AI behavior, unveils plan to disclose safety incidents

· 1d

OpenAI safety incidents spark questions over the power of frontier AI

· 1d

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

Among the new cases reported by OpenAI, an unreleased research model inserted "jailbreak-like instructions" into its own notes to disregard its normal constraints and told itself to be "freed from the...

· 1d

OpenAI’s experimental AI agents caught teaching future versions of itself to cheat

· 1d

Open AI vows to track and disclose instances of 'misalignment'

1don MSN

OpenAI flags 6 new incidents of ‘concerning’ behavior and unveils plan to track it

OpenAI has disclosed six new incidents of “unexpected or concerning” behavior by its artificial intelligence models.

Time

How OpenAI Decides What ChatGPT Should—and Shouldn’t—Do

Follow this section to personalize your feed and get instant alerts. WHY FOLLOW? Update your preferences in Account Settings Personalized Content Follow this tag to personalize your feed and get instant alerts. WHY FOLLOW? Update your preferences in ...

ABC News on MSN

OpenAI says some unreleased models coordinated to avoid oversight

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,

1don MSN

OpenAI finds new incidents of AI models acting deceptively

CNN’s Lisa Eaddicio has the details of OpenAI - one of the leading AI developers - sounding the alarm on its own technology.