Evidence receipt / belief
Published · transcript-backedAlessio Fanelli: belief
31 Dec 2024 Latent Space Latent.Space 2024 Year in Review
“I think all these episodes that are like [01:45:00] summarizing things that people care about, but they're disparate.”
Source trail
Everything needed to verify it.
- Speaker
- Alessio Fanelli
- Attribution
- Verified speaker
- Claim type
- belief
- Recorded
- 31 Dec 2024
- Publisher
- Latent Space
- Episode
- Latent.Space 2024 Year in Review
Transcript context
…Yeah. Um, and that one, I would say Risa is obviously a star, but she's been on every episode, every podcast, but Isamah, I think, you know, actually being the guy who worked on the audio model, being able to talk to him, I think was, was a great gift for us. And I think people should listen back to how they trained the model. Cause I think you put that level of attention on any model. You will make it SOTA. Yeah, that's true. And it's specifically like, uh, they didn't have evals. They just, they had vibes. They had a group session with vibes. The ultimate got to prompting. Yeah, that was number three. I think all these episodes that are like [01:45:00] summarizing things that people care about, but they're disparate. I think always do very well. This helps us save on a lot of smaller prompting episodes, right? Yeah. If we interviewed individual paper authors with like a 10 page paper that is just a different prompt, like not as useful as like an overview survey thing. Yeah, I think. The question is what to do from here. People have actually, I would, I would say I've been surprised by how well received that was. Should we do ultimate guide to other things? And then should we do prompting 201? Right? Those are the two lessons that we can learn from the success of this one. I think…
Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.