絞り込み結果
12 件並び順
1:57:29ENFrontier vision models score 12.5%: Joseph Nelson on the real waterline of computer visionホスト Nathan LabenzThe Roboflow CEO tells Nathan Labenz why vision still lags language, how to distill SAM 3 into an edge model for Wimbledon, and why the United States has almost never led open-source vision.
3:53:49ENWith One-Twelfth the Data, an Open-Source Vision Model Beat GPT-4oホスト Nathan LabenzWill Hardman of Veratai walks Nathan Labenz through two years of vision-language models, from ViT and CLIP to InternVL, BLINK, and Transfusion.
54:45ENA Few Megabytes of Doom and a Few Gigabytes of Model: Why Runway Bets on Generalizationホスト Nathan LabenzCTO Anastasis Germanidis tells The Cognitive Revolution why video is a fuller record of the world than text, why physics shows up without being programmed in, and how a small lab competes with unlimited compute.
46:47ENEditing Video Like a Document: How Descript Puts AI in the Copilot Seatホスト Nathan LabenzDescript CEO Andrew Mason on Underlord, why the timeline had to die, and what a ten-times-more-expensive editor would look like.
1:03:22ENA 40-person team at $35 million ARR: HeyGen made AI avatars a business, not a demoホスト Nathan LabenzJoshua Xu and Benchmark’s Victor Lazarte tell Nathan Labenz how a camera-replacement product grew past 40,000 business customers — and why half the faces on this episode are fake.
1:21:28ENThe Prompt Is a Bug: Suhail Doshi’s Bet on Control Over Pixelsホスト Nathan LabenzThe Mixpanel founder tells Nathan Labenz how a cloud browser, a canceled tweet, and a Thursday weight drop shaped Playground AI’s bet on images.
1:36:39ENOpenAI’s $5 Million Bet: A 60-Person Team Wants GPT-4V to Give Cars Common Senseホスト Nathan LabenzGhost Autonomy cofounder John Hayes tells Cognitive Revolution why a multimodal model on the driving path could reset self-driving after two decades of DARPA-era stacks.
1:30:21ENA Million DALL-E Images, Distilled into Twelve Minutes of Filmホスト Nathan LabenzWaymark’s Stephen Parker and Josh Rubin walk through how they turned stills from DALL-E 2 into The Frost, a narrative short, and what the next generation of video models changes.
1:18:18ENFifteen Thousand Brain Numbers Were Enough to Reconstruct What Someone Sawホスト Nathan LabenzTanishq Mathew Abraham walks through MindEye, the fMRI-to-image system that maps a handful of voxel values onto CLIP and diffusion models.
1:01:17ENThe $300 million Gates refused, and the $10 billion that went to OpenAIホスト Nathan LabenzRobert Scoble and Ben Tossell talk with Nathan Labenz about AI scouting, Apple's still-sleeping neural engines, and whether incumbents or AI-first startups will win.
1:21:20ENFreeze the eyes and the brain. Train only the optic nerve.ホスト Nathan LabenzJunnan Li and Dongxu Li tell Nathan Labenz how BLIP cleaned noisy web captions, and how BLIP-2 connected a frozen vision model to a frozen language model in under ten days on one A100.
1:23:18ENFrom GPT-2 to GPT-3 Moments in Robotics: Six DeepMind Papers on Bridging Robots and the Internetホスト Nathan LabenzKeerthana Gopalakrishnan and Ted Xiao walk through RT-2, RT-X, RT-Trajectory, AutoRT, Learning to Learn Faster and PIVOT, and say what is still missing for general-purpose robots.








