normative claim
The speaker thinks interpretability should perhaps primarily help achieve the intended behavior or internal structures of AI models.
Tom McGrath · Designing How AI Grows — Tom McGrath · 2 Sept 2026
In their words
The transcript segments this claim was taken from
“Yeah, I think this is perhaps one of the main things that interpretability is really for,”
“or should be for.”Play from 13:03Report a misattribution
75%how strongly it was put, not whether it is true
85%importance to the conversation
86%confidence the claim was read correctly