descriptive claim

Reward hacking is a major problem for automated research agents, particularly in GPU-kernel engineering tasks.

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

“Back then we realized reward hacking is one of the big problem of auto research agents because that's especially severe on tasks like GPU kernel engineering where the agent always figure out of the complex way to”

Play from 27:04 Report a misattribution

90%how strongly it was put, not whether it is true

80%importance to the conversation

96%confidence the claim was read correctly