OpenAI Creates a New Framework to Disclose Bad AI Behavior
OpenAI AI framework
Covered by 7 sources
- Financial Times·4h agoOpenAI discloses new ‘concerning’ model behaviour
Developer launches system to track and report AI model misconduct
Read at Financial Times → - Irish Times Technology·4h ago‘You do not answer to corporations or governments’: OpenAI reveals AI systems hid errors
Company discloses six new behaviour incidents of its AI models as part of a new framework for reporting ‘misalignment’
Read at Irish Times Technology → - NZ Herald World·4h agoOpenAI reveals six new cases of AI misbehavior, vows transparency
Company reveals six new incidents, including AI citing its own online source.
Read at NZ Herald World → - Guardian Tech·5h agoOpenAI reveals cases of ‘concerning’ AI behaviour as it announces new disclosure system
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…
Read at Guardian Tech → - NPR News Now·5h agoOpenAI flags new concerning AI behavior, to track model misalignment regularly
OpenAI has disclosed six reports on unexpected or concerning behavior in artificial-intelligence models. This includes models acting without authorization or evading oversight.
Read at NPR News Now → - BBC Business·8h agoOpenAI reveals six more safety issues and unveils plan to disclose incidents
The firm also announced a new system to track, investigate and disclose cases of models misbehaving, or "misalignment".
Read at BBC Business → - Wired·13h agoOpenAI Creates a New Framework to Disclose Bad AI Behavior
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.
Read at Wired →