prediction claim
The speaker speculates that if only one in 100 reinforcement-learning traces incentivizes cheating, the resulting AI systems might be benign and the outcome might be acceptable.
Unresolved speaker · Noam Brown – Agent swarms, alignment, & recursive self-improvement · 17 Sep 2026
In their words
The transcript segments this claim was taken from
“It's like maybe if only one in 100 RL traces incentivizes cheating,”
“we build sweethearts and it's fine.”1:14:43Report a misattribution
0.35how strongly it was put, not whether it is true
0.80importance to the conversation
0.94confidence the claim was read correctly