Ergebnisse
33 ArtikelSortieren
1:57:29EN
Cognitive Revolution "How AI Changes Everything"· 4. Apr. 2026PodcastFrontier vision models score 12.5%: Joseph Nelson on the real waterline of computer visionModeration: 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.
11:31EN
Matthew Berman· 29. Jan. 2026Exploring Google’s Project Genie: Interactive Worlds with Genie 3AlexAlex tests generated racetracks, alien structures and cloud landscapes, showing both the prototype’s creative options and its control limitations.
9:10ENMatthew Berman· 15. Mai 2025Guiding AI Image Generation with Blender and ComfyUIMatthew Berman · Forward FutureMatthew Berman walks through NVIDIA’s RTX blueprint for turning a simple Blender scene and a text prompt into a generated image, from installation to editing the result.
17:03ENMatthew Berman· 28. März 2025Matthew Berman Explores GPT-4o Image Generation and Its LimitsMatthew Berman · Forward FutureFrom animated trailer remakes to infographics and interface mockups, early examples show creative possibilities alongside persistent errors.
3:53:49ENCognitive Revolution "How AI Changes Everything"· 3. Jan. 2025PodcastWith One-Twelfth the Data, an Open-Source Vision Model Beat GPT-4oModeration: Nathan LabenzWill Hardman of Veratai walks Nathan Labenz through two years of vision-language models, from ViT and CLIP to InternVL, BLINK, and Transfusion.
13:31ENMatthew Berman· 19. Dez. 2024Google Veo 2: Cinematic Controls, Realistic Scenes and Motion LimitsMatthew Berman · Forward FutureMatthew Berman reviews Google’s 2024 video-generation examples, compares selected outputs with Sora and points out where movement or prompt adherence breaks down.
14:23ENMatthew Berman· 9. Dez. 2024Sora’s Initial Release: Storyboards, Remix and a Launch-Day TestMatthew Berman · Forward FutureMatthew Berman explores the 2024 video generator’s editing tools and reports mixed results from his first attempts.
54:45ENCognitive Revolution "How AI Changes Everything"· 9. Okt. 2024PodcastA Few Megabytes of Doom and a Few Gigabytes of Model: Why Runway Bets on GeneralizationModeration: 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.
11:14ENMatthew Berman· 18. Sept. 2024Pixtral 12B: Testing a 2024 Vision-Language ModelMatthew Berman · Forward FutureMatthew Berman runs informal image, text and interface-generation tests of Mistral’s Pixtral on a sponsor-provided cloud GPU.
12:17ENMatthew Berman· 7. Aug. 2024Testing Gemini 1.5 Pro on Code, Reasoning, Images and VideoMatthew Berman · Forward FutureMatthew Berman compares standard and experimental Gemini versions in an informal 2024 review, finding mixed results and repeated output errors.
46:47ENCognitive Revolution "How AI Changes Everything"· 3. Aug. 2024PodcastEditing Video Like a Document: How Descript Puts AI in the Copilot SeatModeration: Nathan LabenzDescript CEO Andrew Mason on Underlord, why the timeline had to die, and what a ten-times-more-expensive editor would look like.
1:03:22ENCognitive Revolution "How AI Changes Everything"· 2. Aug. 2024PodcastA 40-person team at $35 million ARR: HeyGen made AI avatars a business, not a demoModeration: 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.
13:37ENMatthew Berman· 16. Mai 2024Testing Gemini 1.5 Pro’s Long Context and Video UnderstandingMatthew Berman · Forward FutureMatthew Berman’s 2024 tests show useful image and video summaries alongside blocked code and missed details.
1:21:28ENCognitive Revolution "How AI Changes Everything"· 26. Jan. 2024PodcastThe Prompt Is a Bug: Suhail Doshi’s Bet on Control Over PixelsModeration: 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.
6:57ENMatthew Berman· 22. Nov. 2023A Camera Narrator Using GPT-4 Vision and ElevenLabsMatthew Berman · Forward FutureMatthew Berman demonstrates a 2023 project that turns webcam frames into spoken nature-documentary-style narration.
1:36:39ENCognitive Revolution "How AI Changes Everything"· 9. Nov. 2023PodcastOpenAI’s $5 Million Bet: A 60-Person Team Wants GPT-4V to Give Cars Common SenseModeration: 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.
1:30:21ENCognitive Revolution "How AI Changes Everything"· 14. Sept. 2023PodcastA Million DALL-E Images, Distilled into Twelve Minutes of FilmModeration: 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.
1:18:18ENCognitive Revolution "How AI Changes Everything"· 20. Juni 2023PodcastFifteen Thousand Brain Numbers Were Enough to Reconstruct What Someone SawModeration: Nathan LabenzTanishq Mathew Abraham walks through MindEye, the fMRI-to-image system that maps a handful of voxel values onto CLIP and diffusion models.
8:09ENMatthew Berman· 12. Juni 2023Text-to-Video in 2023: Runway, Colab and a Local Zeroscope SetupMatthew Berman · Forward FutureMatthew Berman compares a hosted Runway Gen-2 demo with a Zeroscope notebook and a Windows GPU installation, showing the short-clip limitations he encountered.
1:01:17ENCognitive Revolution "How AI Changes Everything"· 9. Mai 2023PodcastThe $300 million Gates refused, and the $10 billion that went to OpenAIModeration: 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.
1:21:20ENCognitive Revolution "How AI Changes Everything"· 9. März 2023PodcastFreeze the eyes and the brain. Train only the optic nerve.Moderation: 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.
9:59EN
Lex FridmanPodcastIs Language or Vision Harder? Ilya Sutskever on the Unity of Machine LearningModeration: Lex FridmanIn a short clip from his 2020 conversation with Lex Fridman, Ilya Sutskever explains why vision, language and reinforcement learning share the same few principles, and why asking which problem is harder is the wrong question.
58:46ENLex FridmanPodcastCaging the Neural Network: How Aptiv Thinks About Safe Self-DrivingModeration: Lex FridmanAptiv Autonomous Mobility's Karl Iagnemma and Oscar Beijbom explain why end-to-end learning is hard to trust in cars, and show how PointPillars and nuScenes push lidar perception forward.
1:23:18ENCognitive Revolution "How AI Changes Everything"PodcastFrom GPT-2 to GPT-3 Moments in Robotics: Six DeepMind Papers on Bridging Robots and the InternetModeration: 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.Mehr laden24 von 33 angezeigt