Chinchilla, every mention

6 scenes · ← back to Chinchilla

tap a year for its mentions
0051102202420252026episodesmentions
012202420252026episodes it came up in
002.5152202420252026episodesmentions per episode

every year anyone Thomas Scialom 7Shawn Wang 1Jeff Dean 1Ari Morcos 1

Verbatim, from the transcripts: the passages where Chinchilla comes up

loading…

The AI Frontier: from Gemini 3 Deep Think distilling to Flash — Jeff Dean Feb 12, 2026 · 1 mention

  • ▶ 1:08:16 Jeff Dean And then Legacy DeepMind had, uh, efforts like, um, chinchilla models and, uh, flamingo models.

Captaining IMO Gold, Deep Think, On-Policy RL, Feeling the AGI in Singapore — Yi Tay Jan 23, 2026 · 1 mention

  • ▶ 56:35 unnamed speaker Last time that we were on the podcast, we talked about chinchilla versus inference optimal training.

Better Data is All You Need — Ari Morcos, Datology Aug 29, 2025 · 1 mention

  • ▶ 8:25 Ari Morcos And even if you go and you look at the scaling laws work from Kaplan and Chinchilla and all these other things, they all assume IID data, um, which is insane.

2024 Year in Review: The Big Scaling Debate, the Four Wars of AI, Top Themes and the Rise of Agents Jan 1, 2025 · 1 mention

  • ▶ 8:32 Shawn Wang Chinchilla paper is compute optimal training, but what is not stated in there is it's pre-trained compute optimal training.

Training Llama 2, 3 & 4: The Path to Open Source AGI — with Thomas Scialom of Meta AI Jul 23, 2024 · 7 mentions

  • ▶ 9:28 Thomas Scialom It's also because the project was taking some routes to reproducing a chinchilla, which was a seven TB. 7 times in the scene

Open Source AI is AI we can Trust — with Soumith Chintala of Meta AI Mar 6, 2024 · 3 mentions

  • ▶ 42:21 unnamed speaker Um, uh, the most interesting thing for, for, for us covering on this, in this podcast was, uh, the death of Chinchilla, as people say. 3 times in the scene
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes 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.