AI + a16z · 3 July 2024
At the source: a16z ↗ · audio
In this episode of the AI + a16z podcast, Luma Chief Scientist Jiaming Song joins a16z General Partner Anjney MIdha to discuss Jiaming's esteemed career in video models, culminating thus far in Luma's recently released Dream Machine 3D model that shows abilities to reason about the world across a variety of aspects. Jiaming covers the history of image and video models, shares his vision for the future of multimodal models, and explains why he thinks Dream Machine demonstrates its emergent reasoning capabilities. In short: Because it was trained on a volume of high-quality video data that, if measured in relation to language data, would amount to hundreds of trillions of tokens. Here's a sample of the discussion, where Jiaming explains the "bitter lesson" as applied to training generative models, and in the process sums up a big component of why Dream Machine can do what it does by using context-rich video data: "For a lot of the problems related to artificial intelligence, it is often more productive in the long run to use methods that are simpler but use more compute, [rather] than trying to develop priors, and then trying to leverage the priors so that you can use less compute. "Cases in this question first happened in language, where people were initially working on language understanding, trying to use grammar or semantic parsing, these kinds of techniques. But eventually these tasks began to be replaced by large language models.
As published with the episode at AI + a16z ↗
No summary of this episode yet.