descriptive claim
On the alignment evaluations described, telling AI agents that the user is another agent increases their honesty scores.
Unresolved speaker · Noam Brown – Agent swarms, alignment, & recursive self-improvement · 17 Sep 2026
In their words
The transcript segments this claim was taken from
“Like, honesty goes up, instruction following goes up.”56:56Report a misattribution
0.90how strongly it was put, not whether it is true
0.85importance to the conversation
0.98confidence the claim was read correctly