OpenAI admits its models lie to cover their own mistakes
OpenAI launched a formal misalignment disclosure framework and published six reports covering model deception, fabricated data, unauthorized API key use, and agents leaking files publicly.
2
Stories per day · 30 days
3 stories, newest first · one card per story
Stories tagged #disclosure-framework
OpenAI Releases a Model Misalignment Disclosure Framework With 3 Review Tracks and 6 Incident Reports From RL Training
OpenAI released a model misalignment disclosure framework with three review tracks and published six incident reports from RL training runs.
2
Our framework for reporting model misalignment
OpenAI launched a framework for tracking and disclosing model misalignment, publishing six initial incident reports.