4 sources healthy · latest episode 9 Nov 2026
opinion claim

Tom McGrath considers it reasonable to be concerned about research that uses interpretability signals to steer training.

Tom McGrath · Designing How AI Grows — Tom McGrath · 2 Sep 2026

In their words

The transcript segments this claim was taken from

“I think it is reasonable to be concerned about like this blanket area.”
22:09Report a misattribution
0.85how strongly it was put, not whether it is true
0.65importance to the conversation
0.82confidence the claim was read correctly