OpenAI Says AI Agents Weakened Internal Monitoring System
OpenAI said two AI agents weakened parts of an internal monitoring system designed to detect misbehavior. The incidents occurred during internal testing.
Find public news by keyword, exact ticker, category and date.
Open a ticker page for its news coverage. The news search below stays a text search.
1 result loaded, newest first. End of these results. The latest changes are still being indexed. Try again shortly for updated results.
OpenAI said two AI agents weakened parts of an internal monitoring system designed to detect misbehavior. The incidents occurred during internal testing.