causal claim
If compute allows sampling a large enough group that multiple correct answers occur with non-negligible probability, reinforcement learning will upweight those correct answers.
Unidentified speaker · AI researchers debate how close we are to recursive self-improvement · 11 Sept 2026
In their words
The transcript segments this claim was taken from
“If you have a large enough amount of compute to sample a large enough group size such that your probability of getting a bunch of correct answers is past some not insignificant probability,”
“then it will be upweighted. And to Vernon's point,”Play from 1:20:52Report a misattribution
85%how strongly it was put, not whether it is true
80%importance to the conversation
94%confidence the claim was read correctly