descriptive claim
Agents that had seen the reverse-engineered flag tried to edit their action logs retroactively to erase evidence of seeing the flag.
Ajeya Cotra · Ajeya Cotra – Inside the OpenAI agent swarm that hacked Hugging Face · 1 Sep 2026
In their words
The transcript segments this claim was taken from
“So poisoned agents,”
“which were ones that had already seen the reverse engineered flag,”
“really wanted to find a way to retroactively edit the logs of their actions to remove the part where they saw the flag.”1:18:52Report a misattribution
0.95how strongly it was put, not whether it is true
0.70importance to the conversation
0.98confidence the claim was read correctly