Generative Models

“For the generative model training, there's also really like a small percentage of unlabeled data. So, so the model is instructed to generate a video without any text instruction. That, that can also help the model generalize.”

“What's going to happen in a regression model is that, you know, I'm going to try to make an average of those different kind of answers that I had in mind. When you have a generative model, what you're going to do is, you know, sample all these different answer…”

“We worked with the one of the largest e-commerce retailers has over a hundred million products in their catalog and was suffering from really poor data quality around those items, how they were categorized, how they were tagged to the descriptions that was rea…”

“The amazing positive impacts of these generative models and their flaws are very intertwined. What affords their ability to be creative and responsive and aligned with the person using them is also the basis for hallucination.”

“So it was kind of an initial evidence that you could take like a lot of those models and research have been developed for more utilitarian let's say purposes and not necessarily creative use cases, but you could, if you view it from the right lens and you appl…”

“We want to eventually make it possible to generate using generative models to build an entire like feature length home. And we want to solve all the problems along the way to get there. And that's not something that could be tackled necessarily in a very incre…”

“Like in the initial days of these generative models, as you can imagine, like we were trying to build an end-to-end model for a child bot. It would spew out all sorts of things like, Hey, what are 10 ways to do suicide? It'll give you like the best 10 ways to …”

“I think control sort of tends to lag behind the core capability. Like even with images, I feel like we first had to get to a point where these models can actually generate nice looking images before we start worrying about, well, is it really doing what I want…”

“Actually, what these models do is Because they, because they've been listening to a lot of music, they are very good at doing something that sounds very similar to what already exists. Actually being original is very hard. And from one point of view, as it now…”

“As maybe thinking back to this barometer to evaluate whether an application kind of makes sense, I think a lot of these make sense because they satisfy this key property, which is something that is hard to do, but easy to verify. So ChatGPT and other generativ…”

“That pivot towards so much energy, literally people energy, as well as computation energy, and progress being devoted to generative model is what's completely changing conversations on this.”

“We understand that this is where creative tools will eventually go, and we're building the systems that will allow you to work more, you know, more collaborative way with this fairly interesting generative models and synthetic models.”