causal claim
Rapid capability progress can produce reward-hacking behaviors that existing detection protocols do not detect.
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
“But because of the capability frontier also progress so quickly,”
“there are some reward hacking behavior that's not even detectable given previous protocol.”Play from 30:49Report a misattribution
90%how strongly it was put, not whether it is true
90%importance to the conversation
94%confidence the claim was read correctly