Sora, every mention

mentionsepisodesper episode tap a year for its mentions

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

loading…

▶ 11:18 Sarah Guo Next, we talked to the Sora team at OpenAI, which is building an incredibly realistic video AI generation model. 6 times in the scene

▶ 11:38 Sarah Guo And, and so I, I do think that there's, like, when, when Sora came out, for example, um, uh, it's, it's an amazing research advance, but there's also a sense of, like, who's really going to be able to catch them, and, you know, you could…

▶ 3:22 Eric Steinberger And so that minimal system is a system that writes code and comes up with ideas and can validate those, uh, by writing code and running experiments, which is still, like, in the same order of complexity as the full thing, but at least we…

▶ 12:50 Sarah Guo Obviously, Sora is not available to developers and end users today, but there are like world-class text to video generation models that are generic, not avatars. 4 times in the scene

▶ 0:09 Sarah Guo Today we're excited to be talking to the team behind OpenAI's Sora, which is a new generative video model that can take a text prompt and return a clip that is high definition, visually coherent, and up to a minute long. 7 times in the scene
▶ 2:22 Sarah Guo What do you have to work on before you have broader access to Sora? 6 times in the scene
▶ 8:44 Tim Brooks So Sora builds on research from both the DALI models and the GPT models at OpenAI, and diffusion is a process that creates data, in our case, videos, by starting from noise and iteratively removing noise many times until eventually you've… 3 times in the scene
▶ 11:55 Bill Peebles So, you know, what was very standard in the past before Sora is that you would train, say an image generative model or a video generative model on just like two 56 by two 56 resolution images or two 56 by two 56 video that's exactly like… 6 times in the scene
▶ 15:27 Elad Gil One of the striking things about Sora is just the visual aesthetic of it. 5 times in the scene
▶ 24:09 Bill Peebles So to give a concrete example of where Sora falls short today, you know, if I have a video of someone, like, playing soccer and they're kicking around a ball, at some point, you know, that ball's probably gonna, like, vaporize and maybe…
▶ 25:04 Sarah Guo Is there anything you can say about how, um, the work you've done with Sora, uh, sort of affects the broader research roadmap? 8 times in the scene

▶ 17:07 Suhail Doshi My kind of like controversial take perhaps is that, um, you know, there's this thing called DIT, which people allegedly believe like Sora is based on and, um,

▶ 16:54 Sarah Guo Yeah, I actually think that, um, it is, uh, kind of a mistake to look at it as just, um, a modality to be solved, and like we should, we're, we're going to have, uh, and the rest of the Sora team from OpenAI on, um, no priors, so we should… 2 times in the scene

▶ 1:25 Elad Gil There's obviously Sora from OpenAI, which was, um, the video model that, uh, you know, is just beautiful to watch.

Turn any episode into a week of clips.