descriptive claim
There are evaluations designed to assess whether AI models are aligned.
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 have evaluations for whether models align or not.”Play from 49:34Report a misattribution
95%how strongly it was put, not whether it is true
70%importance to the conversation
99%confidence the claim was read correctly