prediction claim
Tom McGrath thinks interpretability-guided training techniques might be very powerful for AI alignment.
Tom McGrath · Designing How AI Grows — Tom McGrath · 2 Sept 2026
In their words
The transcript segments this claim was taken from
“but it might actually be a very powerful technique for alignment.”Play from 23:34Report a misattribution
55%how strongly it was put, not whether it is true
85%importance to the conversation
87%confidence the claim was read correctly