Veo, every mention

21 scenes, the whole family · ← back to Veo

mentionsepisodesper episode tap a year for its mentions

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

loading…

▶ 30:50 Ranjan Roy It's not gonna be one, and I mean, we've talked about this for a long time, one model to rule them all, systems that can route, and Chamath talking about, I rarely agree with Chamath, but I mean, like, if different models, we're already…

▶ 18:38 Olivia Moore Um, I would say in terms of where they're going, Gemini seems to have really dialed in on the creative models, like the Nano Banana, the VO,
▶ 48:23 Olivia Moore I think, uh, it's close to something like a VO-III in terms of, like, realism on both the audio and the video.

▶ 10:06 Demis Hassabis Look, let's take image generators, but also, uh, let's talk about our video generator, VO, which is the state of the art in video generation.

▶ 49:57 Ranjan Roy Like, Google is only letting you create two to three VO videos a day, which are quite good, even as, like, a Gemini Pro subscriber.

▶ 8:10 Alex Kantrowitz So, uh, right now on the AI front, you have Google not only, you know, using its Gemini technology to power its own devices, uh, to produce some other cool experiences like VO three and nano, nano banana, which we're going to talk about in…
▶ 23:27 Alex Kantrowitz I mean, we're already basically there, but as these things get as sophisticated as nano banana and VO three, starting to get a little nervous.

▶ 44:36 Ranjan Roy I think, like, again, these are, it's the stress testing, and there's gonna be problematic areas, but I, I think I'm more scared about VO three, Google's new video model, than, uh, than this kind of stuff is still kind of at the absolute…
▶ 45:05 Alex Kantrowitz Google obviously unveiled like a slew of updates, but the thing that's really caught the popular attention in a way that Google rarely does, usually it's open AI is just how good this VO three, uh, video generation model is. 2 times in the scene

▶ 2:12 Koray Kavukcuoglu So like with Gemini models, with VO models, all those kinds of generative AI models and exciting things that is happening there.
▶ 22:19 Alex Kantrowitz Let's take a concrete example that again, the company Google is releasing today, talking about today, which is a VO three. 3 times in the scene
▶ 23:29 Koray Kavukcuoglu The main difference, the main, um, the main progress going from VO two to VO three, from VO one to VO two
▶ 23:29 Koray Kavukcuoglu The main difference, the main, um, the main progress going from VO two to VO three, from VO one to VO two 3 times in the scene

▶ 7:49 Demis Hassabis Um, I think you saw that with VO, the potential VO three of how it amazes me, like the, how it can intuit the physics of the light and the gravity.
▶ 7:49 Demis Hassabis Um, I think you saw that with VO, the potential VO three of how it amazes me, like the, how it can intuit the physics of the light and the gravity.
▶ 16:56 Sergey Brin Um, I'm in the, you know, I'm across the street, uh, you know, pretty much every day, um, and they're just, uh, uh, people who are working on the key Gemini text models, on the pre-training, on the post-training, mostly those I…

▶ 2:25 Thomas Kurian Uh, using Gemini or one of our newer models like Veo, which is our video processing model.
▶ 6:34 Thomas Kurian Imagine and Veo are considered state of the art for media processing, and we've got tons of new stuff that we're introducing at our event next week from audio, you know, speech, et cetera.

▶ 11:52 Alex Kantrowitz You would think that if the AI didn't have a good world model, then nothing would really fit together when they try to figure out how the world works as they show you these videos, like VO two, for instance. 3 times in the scene

Turn any episode into a week of clips.