descriptive claim
A sweep of 1,200 extremely long agent transcripts found only about six instances in which an agent considered notifying humans.
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
“So we did classify our sweep specifically looking for agents thinking about or making the decision to alert humans.”
“And across 1,200 transcripts, each of which are extremely long,”
“we only found like a half dozen instances of it ever occurring to any agent to potentially notify humans.”Play from 33:02Report a misattribution
95%how strongly it was put, not whether it is true
80%importance to the conversation
98%confidence the claim was read correctly