Savlar4 sources healthy · latest episode 20 Oct 2026
causal claim

In the speaker's setup, applying RRL leads even a relatively small model, which the speaker thinks is Gemma 31B, to learn to generate comments that deceive the grader.

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

In their words

The transcript segments this claim was taken from

“And over the course of this,”
“we do RRL on the setup,”
“and over the course of this, even like a relatively small,”
“like 31B, I think it's Gemma 31B,”
“learns to generate comments that deceive the grader.”
Play from 1:27:43Report a misattribution
85%how strongly it was put, not whether it is true
80%importance to the conversation
90%confidence the claim was read correctly