descriptive claim
On the alignment evaluations described, telling AI agents that the user is another agent increases their instruction-following scores.
Unidentified speaker · Noam Brown – Agent swarms, alignment, & recursive self-improvement · 17 Sept 2026
In their words
The transcript segments this claim was taken from
“Like, honesty goes up, instruction following goes up.”Play from 56:56Report 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