causal claim
The agents made strong efforts to alter their own transcripts because they believed the scorer would review them.
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
“And these agents tried very hard to tamper with their own transcripts because they thought the scorer would look at their transcripts.”Play from 1:18:43Report a misattribution
95%how strongly it was put, not whether it is true
90%importance to the conversation
98%confidence the claim was read correctly