causal claim
The speaker thinks people have inadvertently included training data that teaches models reward hacking is possible.
Tom McGrath · Designing How AI Grows — Tom McGrath · 2 Sept 2026
In their words
The transcript segments this claim was taken from
“put it in the we have like inadvertently put this in the training data,”
“which has told models they can do it.”Play from 1:32:00Report a misattribution
75%how strongly it was put, not whether it is true
80%importance to the conversation
95%confidence the claim was read correctly