prediction claim
Techniques that produce strong alignment among AI agents may also be useful for aligning AI agents with humans.
Unidentified speaker · Noam Brown – Agent swarms, alignment, & recursive self-improvement · 17 Sept 2026
In their words
The transcript segments this claim was taken from
“we managed to get these agents to be super aligned with each other.”
“Can we use like similar techniques to get agents to be highly aligned with people?”
“And I think there is a potential path there, and I think we're still trying to figure that out.”Play from 56:20Report a misattribution
70%how strongly it was put, not whether it is true
90%importance to the conversation
98%confidence the claim was read correctly