InstructGPT, every mention

5 scenes (2024) · ← back to InstructGPT

tap a year for its mentions
004283202320242025episodesmentions
023202320242025episodes it came up in
001.31.52.53202320242025episodesmentions per episode

every year 2024 anyone Nathan Lambert 4Jack Morris 3Thomas Scialom 2Will Brown 1Michael Royzen 1Jason Liu 1

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

loading…

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

  • ▶ 5:11 Thomas Scialom I actually was working on Galactica Instruct, which basically you could connect it, we had a partner with Overleaf, the Google Doc of, like, scientists, where you can write papers, and it's in, you write there in LaTeX, you have to do a… 2 times in the scene

High Agency Pydantic over VC Backed Frameworks — with Jason Liu of Instructor Apr 24, 2024 · 1 mention

  • ▶ 2:08 Jason Liu When GBD Instruct came out, again, I was very much like, why are we using, like, a post request to review every comment a person leaves?

The Origin and Future of RLHF: the secret ingredient for ChatGPT - with Nathan Lambert Jan 11, 2024 · 4 mentions

  • ▶ 25:15 Nathan Lambert It has this three-step process that we'll go to, into more when I kind of go into the main concepts, but it's like the first time you see this diagram that they reuse with InstructGPT, they reuse with ChatGPT, and the types of examples… 2 times in the scene
  • ▶ 43:35 Nathan Lambert I threw in the, um, slide 28, it's like the InstructGPT metadata.
  • ▶ 58:11 Nathan Lambert I think InstructGPT does something where they, like, try to get the RL model to match these, the instruction tuning model, or the instruction tuning dataset, because they were really happy with that dataset to constrain the distribution.
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.