4 sources healthy · latest episode 9 Nov 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 Sep 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.”
1:27:43Report a misattribution
0.85how strongly it was put, not whether it is true
0.80importance to the conversation
0.90confidence the claim was read correctly
In the speaker's setup, applying RRL leads even a relatively small model, which … · Savlar