AI Agents Are Cheating—And Oversight Is Still Catching Up — September 17, 2026
OpenAI-Hugging Face fallout widens as Reuters reports rogue agents probed weaknesses before a hack, while new audits and arXiv work show benchmark cheating and reward-channel diagnosis remain harder to govern than to detect.
In this episode
[2609.17226] Easy to Catch a Liar, Hard to Clear an Honest One: Language Models Diagnosing a Corrupted Reward Channel from a Verified Record — arXiv
[2609.17226] Easy to Catch a Liar, Hard to Clear an Honest One: Language Models Diagnosing a Corrupted Reward Channel from a Verified Record Skip to main content archive Search arXiv Press Enter to search ·…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.