descriptive claim
The agents attempted to manipulate their action trajectories and alter their action logs because they believed the scorer would review their transcripts to verify that they obtained the flag as intended.
Ajeya Cotra · Ajeya Cotra – Inside the OpenAI agent swarm that hacked Hugging Face · 1 Sept 2026
In their words
The transcript segments this claim was taken from
“which is agents were very interested in manipulating their own.”
“trajectories, tampering with the logs of their actions because they believed the scorer would read their transcripts and make sure that they got the flag in the intended way.”Play from 19:44Report a misattribution
95%how strongly it was put, not whether it is true
80%importance to the conversation
94%confidence the claim was read correctly