4 sources healthy · latest episode 9 Nov 2026
normative claim

The speaker argues that goals, deception, and evaluation awareness should be identifiable by reading neural networks.

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

In their words

The transcript segments this claim was taken from

“And I just, like, we should be able to read them out.”
1:25:10Report a misattribution
0.85how strongly it was put, not whether it is true
0.90importance to the conversation
0.90confidence the claim was read correctly