Logits

topic on 1 show · 2 statements across 2 episodes

2 statements about Logits, every show

Jeff Dean: Teacher model logits enable small models to learn from multi-pass training

“One of the key advantages of distillation is that you can have a much smaller model And you can have a very large you know, training data set and you can get utility out of making many passes over that data set because you're now getting the logits from the mu…”

Jeff Dean Feb 12, 2026 ▶ 6:02 The AI Frontier: from Gemini 3 Deep Think distilling to Flash — Jeff Dean

LATENT SPACE Opinion

Agarwal: Developers should use logit distillation over synthetic data for open models

“But for open models, yeah, you can do better because you have access to logits, so why not use them? At least that's my take.”

Rishabh Agarwal Mar 23, 2025 ▶ 15:29 The Magic of LLM Distillation — Rishabh Agarwal, Google DeepMind

← every entity, every show

Turn any episode into a week of clips.

This entire site, thousands of episodes across every show 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.

Logits

2 statements about Logits, every show

Turn any episode into a week of clips.