GPT-2, every mention
8 scenes · ← back to GPT-2
tap a year for its mentions
every year anyone Francois Chaubard 4Sam Altman 1Raza Habib 1Nick Joseph 1Diana Hu 1Bob McGrew 1
Verbatim, from the transcripts: the passages where GPT-2 comes up
Recursion Is The Next Scaling Law In AI · Y Combinator
- ▶ 4:08 Francois Chaubard Yeah, and so, um, I guess we go back to chat GPT-II. 2 times in the scene
- ▶ 6:30 Francois Chaubard Yeah, so if we, let's just talk about like chat GPT-II, GPT-II, the original, like no bells and whistles, um, it's just a feed forward model, and so it's just forward passing one step, and taking an input, creating a bunch of outputs.
- ▶ 17:31 Francois Chaubard We did this COT stuff and this tool use thing as ways to get beyond the limitations of GPT-II.
Anthropic Head of Pretraining on Scaling Laws, Compute, and the Future of AI · Y Combinator
- ▶ 4:21 Nick Joseph And one of the findings from my GPT-one, GPT-two was kind of, as you throw more compute at this, more data, bigger models,
Bob McGrew: AI Agents And The Path To AGI · Y Combinator
- ▶ 4:34 Bob McGrew And then, uh, after GPT-ONE seemed successful, we brought in the ideas from Dota and from the robot hand of training at, you know, larger and larger amounts of scale and training on a really diverse set of data, uh, and looking for…
How To Build The Future: Sam Altman · Y Combinator
- ▶ 25:42 Sam Altman You know, it was Alex, so it took people a while to, I think, fully internalize what a big deal it was, and he then did GPT-I, and somebody else scaled it up into GPT-II, but it was off of this insight that there was something, uh, amazing…
The 10 Trillion Parameter AI Model With 300 IQ · Y Combinator
The REAL potential of generative AI · Y Combinator
- ▶ 2:38 Raza Habib And so where we are today is that, you know, I think starting from GPT one and two, but then GPT three was really the one that I think everyone said, okay, something is very, very different here.