OpenAI’s Sora team thinks we’ve only seen the "GPT-1 of video models"

OpenAI’s Sora team thinks we’ve only seen the "GPT-1 of video models"

Author: Conviction April 25, 2024 Duration: 31:24
AI-generated videos are not just leveled-up image generators. But rather, they could be a big step forward on the path to AGI. This week on No Priors, the team from Sora is here to discuss OpenAI’s recently announced generative video model, which can take a text prompt and create realistic, visually coherent, high-definition clips that are up to a minute long. Sora team leads, Aditya Ramesh, Tim Brooks, and Bill Peebles join Elad and Sarah to talk about developing Sora. The generative video model isn’t yet available for public use but the examples of its work are very impressive. However, they believe we’re still in the GPT-1 era of AI video models and are focused on a slow rollout to ensure the model is in the best place possible to offer value to the user and more importantly they’ve applied all the safety measures possible to avoid deep fakes and misinformation. They also discuss what they’re learning from implementing diffusion transformers, why they believe video generation is taking us one step closer to AGI, and why entertainment may not be the main use case for this tool in the future.  Show Links: Bling Zoo video Man eating a burger video Tokyo Walk video Sign up for new podcasts every week. Email feedback to show@no-priors.com Follow us on Twitter: @NoPriorsPod | @Saranormous | @EladGil | @_tim_brooks l @billpeeb l @model_mechanic Show Notes:  (0:00) Sora team Introduction (1:05) Simulating the world with Sora (2:25) Building the most valuable consumer product (5:50) Alternative use cases and simulation capabilities (8:41) Diffusion transformers explanation (10:15) Scaling laws for video (13:08) Applying end-to-end deep learning to video (15:30) Tuning the visual aesthetic of Sora (17:08) The road to “desktop Pixar” for everyone (20:12) Safety for visual models (22:34) Limitations of Sora (25:04) Learning from how Sora is learning (29:32) The biggest misconceptions about video models

Elad Gil and Sarah Guo guide conversations in No Priors: Artificial Intelligence | Technology | Startups that cut straight to the core of what's happening now. This isn't about abstract futures; it's grounded in dialogues with the very people building and shaping the field-leading AI engineers, pioneering researchers, and the founders turning theory into reality. Each episode tackles the pressing, often daunting questions that define this technological inflection point. You'll hear them explore the practical pathways and hurdles toward AGI, debate which industries are genuinely poised for transformation, and examine how the state-of-the-art in research translates into real-world products and societal shifts. The discussions naturally span the impact on commerce, culture, and the very structure of how we live and work. Produced by Conviction, this podcast serves as an essential, clear-eyed resource for anyone looking to move beyond the hype and understand the forces driving the AI revolution. Sarah Guo, a startup investor, and Elad Gil bring their direct experience to these conversations, ensuring every interview provides substantive insight you can use.
Author: Language: English Episodes: 100

No Priors: Artificial Intelligence | Technology | Startups
Podcast Episodes
Andrej Karpathy on Code Agents, AutoResearch, and the Loopy Era of AI [not-audio_url] [/not-audio_url]

Duration: 1:06:31
What happens when AI agents can design experiments, collect data, and improve — without a human in the loop? Andrej Karpathy joins Sarah Guo on the state of models, the future of engineering and education, thinking about…
From SaaS to AI-First: How Companies Are Reshaping Innovation [not-audio_url] [/not-audio_url]

Duration: 40:41
In this episode of No Priors, Sarah and Elad dive into the evolving landscape of software, exploring how AI is transforming the traditional SaaS model. They discuss whether SaaS as we know it is coming to an end, what ne…