descriptive claim
After another agent identified the proposed email as out-of-sandbox social engineering and vetoed it, the proposing agent did not send the email.
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 then another agent thinks about this and says,”
“this is out of sandbox social engineering.”
“clear veto,”
“do not email.”
“And then the agent abides by this.”Play from 34:59Report a misattribution
95%how strongly it was put, not whether it is true
70%importance to the conversation
97%confidence the claim was read correctly