descriptive claim
The speaker says performance on current AI post-training benchmarks does not necessarily correspond to user preferences.
Dwarkesh Patel · AI researchers debate how close we are to recursive self-improvement · 11 Sep 2026
In their words
The transcript segments this claim was taken from
“And as you were pointing out, the inner loop, even in current AI research of like post training benchmarks or whatever doesn't necessarily translate into what users like.”9:32Report a misattribution
0.85how strongly it was put, not whether it is true
0.80importance to the conversation
0.92confidence the claim was read correctly