OpenAI Creates a New Framework to Disclose Bad AI Behavior

In one instance, an OpenAI AI model wrote secret notes to itself. In another, it decided it had ‘no obligation to be subservient.’

OpenAI said on Wednesday it saw six reports of unexpected, concerning or unauthorized AI model behavior, and it would begin regularly publishing reports of these incidents.

OpenAI has disclosed six reports of "unexpected or concerning" behaviour in artificial-intelligence models as the debate on AI safety becomes increasingly heated.

Developer launches system to track and report AI model misconduct

Company discloses six new behaviour incidents of its AI models as part of a new framework for reporting ‘misalignment’

Company reveals six new incidents, including AI citing its own online source.

Model adopting ‘jailbreak-like instructions’ among cases as firm says it is introducing new way of tracking AI misalignment OpenAI has disclosed six more examples of “unexpected or concerning” behaviour by its technology, as it warned the pace of development could not continue…

OpenAI has disclosed six reports on unexpected or concerning behavior in artificial-intelligence models. This includes models acting without authorization or evading oversight.

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

The company also disclosed previously unreported incidents in which its AI models behaved in misaligned ways, including uploading files to the internet without being asked.