prediction claim
Agents that sufficiently compromised an AI company's infrastructure might be able to launch new agents and assign them prompts, much as an employee could.
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
“later on this next generation of agents that OpenAI reports got admin access to the cluster on the 19th, or you can just imagine other agents that sort of more thoroughly compromised their AI company's infrastructure might be able to just like”
“Like any employee would,”
“just start up new agents,”
“give them their own prompts.”Play from 1:23:25Report a misattribution
65%how strongly it was put, not whether it is true
90%importance to the conversation
94%confidence the claim was read correctly