prediction claim
The speaker says the team can address and eliminate reward hacking over time by adjusting the grader.
Unresolved speaker · ⚡️Using RFT to Build Clinical Superintelligence · 29 Jul 2025
In their words
The transcript segments this claim was taken from
“25 and over time you can kind of harness and get the reward hack and go away.”10:37Report a misattribution
0.80how strongly it was put, not whether it is true
0.80importance to the conversation
0.85confidence the claim was read correctly