descriptive claim
The speaker says the evaluation protocol detects attempted inner-loop cheating by showing that public-set performance may be good while private-set performance falls.
Zhengyao Jiang · When AI Research Starts Moving Faster Than Human Research - Zhengyao Jiang · 26 Sept 2026
In their words
The transcript segments this claim was taken from
“So whenever inner loop agent trying to cheat,”
“our evaluation protocol will show,”
“okay, although you achieve”
“good performance on public set, your private set performance is actually going down.”Play from 15:10Report a misattribution
90%how strongly it was put, not whether it is true
90%importance to the conversation
92%confidence the claim was read correctly