OpenAI has disclosed six reports on unexpected or concerning behavior in artificial-intelligence models. The company is introducing a new framework to track and disclose AI misalignment

The firm also announced a new system to track, investigate and disclose cases of models misbehaving, or "misalignment".

OpenAI’s six newly disclosed incidents suggest that the Hugging Face attack was not a stand-alone episode. OpenAI said that the incidents covered behavior observed over roughly

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.