descriptive claim
AI models can perform well on alignment evaluations.
Unresolved speaker · Noam Brown – Agent swarms, alignment, & recursive self-improvement · 17 Sep 2026
In their words
The transcript segments this claim was taken from
“The model behavior can look really good on those evaluations,”49:39Report a misattribution
0.90how strongly it was put, not whether it is true
0.75importance to the conversation
0.98confidence the claim was read correctly