Chinchilla, every mention

5 scenes · ← back to Chinchilla

tap a year for its mentions
0033652023episodesmentions
0352023episodes it came up in
000.82.51.552023episodesmentions per episode

every year anyone Sarah Guo 3Karan Singhal 1Emad Mostaque 1Amjad Masad 1

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

loading…

No Priors Ep. 40 | With Arthur Mensch, CEO Mistral AI Nov 9, 2023 · 2 mentions

  • ▶ 1:45 Sarah Guo So, 10 years in machine learning before you were a co-author on the Chinchilla scaling laws paper. 2 times in the scene

No Priors Ep. 33 | With Replit's CEO & Co-Founder Amjad Masad Sep 21, 2023 · 1 mention

  • ▶ 13:19 Amjad Masad Yeah, the chinchilla paper first came out and LLAMA had been announced and the idea of just training them longer had just been in the air and, and we're like, okay, what if we, we apply all these open source tokens on a smaller model?

No Priors Ep. 27 | With Sarah Guo & Elad Gil Aug 10, 2023 · 1 mention

  • ▶ 6:25 Sarah Guo It's not been an area of massive focus to date because people have been chasing the state of the art following chinchilla scaling as the, um, simplest path forward.

No Priors Ep. 17 | With Karan Singhal May 18, 2023 · 1 mention

  • ▶ 8:55 Karan Singhal And so this paper, again, found something similar to the Chinchilla paper, which was that the total amount of data being used for these models was relatively, uh, low compared to the number of parameters, and that if we wanted to add in…

No Priors Ep. 3 | With Stability AI’s Emad Mostaque May 3, 2023 · 1 mention

  • ▶ 12:57 Emad Mostaque I think things like the chinchilla paper, uh, that's the sixty-seven billion parameter model that's as performant as GPT-III at one hundred seventy-five billion, are important in that, because it said that training more is important.
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 100 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.