large-scale RL

1 statements across 1 episodes · 1 bullish · 0 bearish · 1 people on the record · first statement Jan 15, 2026 by Pavel Izmailov · across every show →

Everything said about large-scale RL, oldest first

Jan 15, 2026 positive
Assertion Not checkable as stated
Izmailov: Large-scale RL has not produced coherently misaligned models
“A lot of people were worried that with large-scale RL, we will have Some completely new types of issues with the models, like this kind of coherent misalignment that will just emerge where the models are evil in some ways across many scenarios. And we are not …”
Pavel Izmailov Jan 15, 2026 ▶ 21:47 The Evaluators Are Being Evaluated — Pavel Izmailov (Anthropic/NYU)
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 400 conversations transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.