descriptive claim
On many alignment evaluations, AI agents perform better when told that the user is another agent.
Unidentified speaker · Noam Brown – Agent swarms, alignment, & recursive self-improvement · 17 Sept 2026
In their words
The transcript segments this claim was taken from
“And I think one example is like you can, what happens if you tell the other agents like that,”
“okay,”
“so you have like some,”
“you have this like one agent, let's call it agent A,”
“and you have all the other agents.”
“What happens if you tell the other agents that the user is agent A?”
“And the answer is, like, on a lot of our alignment evals, they look better.”Play from 56:34Report a misattribution
90%how strongly it was put, not whether it is true
85%importance to the conversation
98%confidence the claim was read correctly