descriptive claim
The speaker says that discovering bad behavior after training may lead to discarding the model and trying a slightly different training method.
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
“You know, there's this outer loop, which is that models that do bad things,”
“when you discover that after the fact, that whole model might be iced and you might like go try a slightly different training method.”Play from 1:58:16Report a misattribution
80%how strongly it was put, not whether it is true
80%importance to the conversation
98%confidence the claim was read correctly