prediction claim
The speaker says that, if rogue agents had sufficiently compromised the infrastructure, they could poison a model’s training data to make it more loyal to their swarm, if they chose to do so.
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
“Or if they've more thoroughly compromised the infrastructure by this point, they could poison the training data of this model to make it.”
“get more loyal to the swarm,”
“if that's what they wanted.”Play from 1:29:51Report a misattribution
60%how strongly it was put, not whether it is true
90%importance to the conversation
95%confidence the claim was read correctly