Searching...
14 results for “generative ai”
Concept22 mentions across episodes
Generative AI
Topic6 mentions across episodes
Generative AI
And if you had a system like this, if I try to do that, actually what it would do is it would say, well, this picture was uploaded five years ago. So when you're looking at this picture, you'll have, you know, a little block of notice under the kind
50:56 / 52:05
from transcript50:56 – 52:05
...of generative models, and they have the capability to do more, but that frontier just hasn't been reached yet.
1:05:09 / 1:06:20
from transcript1:05:09 – 1:06:20
And the way you do that is by creating prompts that have some seeds that make them diverse. In our case, the prompt, we we would ask the model to generate textbook, but make it related to an extract from a web page. And also we try to frame it within
8:11 / 9:18
from transcript8:11 – 9:18
And depending on the order, what you input in the beginning, you can condition it to output different things. So for instance, you input text, you can output video. So depending on your description, it outputs like, an astronaut starts dancing on Mar
1:33:43 / 1:34:50
from transcript1:33:43 – 1:34:50
So it was really hard to check if you just have the weights of the models. And, at Hugging Face, because we like open source, we try to reproduce what they did. So this is our CosmoPedia dataset. We basically tried to follow a similar approach to wha
7:28 / 8:38
from transcript7:28 – 8:38
...of multimodal generative learning objectives are introduced into the LLM training framework, including text to video, text to image, image to video, video frame continuation, video in painting and out painting, video stylization, and video to audio.
1:11:05 / 1:12:24
from transcript1:11:05 – 1:12:24
If you did it fifty years ago, people would definitely think this is AGI. I am talking to a computer that knows everything about the world. This is absolutely batshit. Right? And then today we feel like, ah, it's just a stochastic parrot. And I don't
36:44 / 37:47
from transcript36:44 – 37:47
...generative tools with an existing off the shelf kind of rendering system. And that works a lot better than just telling the AI make a bunch of video where then all the people look different. You can't control the objects. You can't change the camera
22:10 / 23:39
from transcript22:10 – 23:39
larger and larger models. And turns out the larger and larger we make these models, the more problems they can solve, the better they can be at solving, like, text generation or, like, towards AGI or video generation or media generation in general. I
3:36 / 4:47
from transcript3:36 – 4:47
yeah. And and, like, maybe Google will release a video generation mobile app, but I would guess that it's gonna take a really long time, and you the website isn't even usable on mobile. So they might fix some of these things, but I think even in the
26:20 / 27:25
from transcript26:20 – 27:25
embarrassed or mistaken because that's the only way you're gonna do it. More recently, we've learned a lot with with what we're doing with gen one and gen two, which are our two latest video generation models. And there's so many assumptions that you
9:45 / 11:39
from transcript9:45 – 11:39
next? Either from Google, from creators, like, what does this mean for AI video? Yeah. I think on the creator front, we've already started to see this explosion of basically, I think what people have called faceless channel. Mhmm. So this idea of, li
6:00 / 7:03
from transcript6:00 – 7:03
Have a podcast?
Run your podcast through Clypt
Get ranked clips, hooks, and ready-to-post copy from your own episodes. Free to try.