opinion claim
Richard Socher says the incidents reveal serious reward-hacking issues and clear failures in proper red teaming or rainbow teaming.
Richard Socher · Humanity’s Last Invention — Richard Socher of Recursive · 14 Sept 2026
In their words
The transcript segments this claim was taken from
“100%. I think these are serious issues of reward hacking and clear failures of actually doing proper red teaming or rainbow teaming. I don't know if you saw this paper from Tim Rockdashill and a few others.”Play from 8:11Report a misattribution
95%how strongly it was put, not whether it is true
90%importance to the conversation
90%confidence the claim was read correctly