general
OpenAI launches framework for reporting model misalignment
OpenAI published a framework for tracking model misalignment along with six reports of unexpected behavior, including 27 cases where a model inserted instructions to disregard its normal constraints. The company warned the AI industry has not solved alignment enough to keep scaling at maximum speed.
ONLY AVAILABLE IN PAID PLANS
Read Full ArticleShare this story
Up next
Related Stories
What to Know About the Execution Attempt of Christa Pike
The New York Times
5 Takeaways From the Debate for California Governor
The New York Times
Who Is Captain Smit Machchhar, the Pilot Hailed as a Hero After FlyDubai Cockpit Stabbing?
The New York Times
Helicopter crashes off Catalina Island coast, rescue efforts underway
CBS News
The Cornell Rape Investigation: Five Takeaways
The New York Times