CEOInterviews.AI
Start App
Try: AI strategy tariffs earnings guidance layoffs interest rates growth

Gorkem Yurtseven

Co-founder & CTO, Fal

Search every verified Gorkem Yurtseven interview, podcast appearance, and on-the-record quote — each transcript cross-checked by AI and human review to confirm speaker identity. Gorkem Yurtseven, co-founder and CTO of fal, discussed the company's work on real-time AI video generation in a September 2026 podcast appearance with a16z General Partner Jennifer Li and fal's Head of Engineering Batuhan Taskaya. He described fal's post-trained version of MiniMax's open-weight video model, H3 Max, and said that combining model post-training with systems and hardware optimization reduced generation time while maintaining quality. He noted that a public version called H3 Max Turbo can generate a five-second video in about 1.5 seconds at roughly half the cost, and that this speed has enabled experiments with continuous video streams that can remember previous scenes and respond to new directions. Yurtseven said the speed improvement was surprising to his team and that it unlocked new workflows for Hollywood and professional users, including using large language models in tools like Blender. He stated that fal built infrastructure for streaming video with low latency and multiplexing to multiple users, and that his ML team applied optimizations to extend generation from five-second clips to longer durations. He also mentioned that fal's upcoming generative media conference has seen attendance shift from consumer AI to include both new AI-focused studios and major Hollywood studios planning to integrate AI into their workflows. He attributed the increased interest partly to the availability of US-hosted models, which he said removed obstacles for those studios.

Recent appearances

  • How Real-Time AI Video Is Changing How Creators Work

    a16z General Partner Jennifer Li sits down with fal co-founder Gorkem Yurtseven and Head of Engineering Batuhan Taskaya to discuss what changes when generative video becomes fast enough to run in real time. They unpack the technical work behind H3 Max, fal’s post-trained version of MiniMax’s open-weight video model, and how combining model post-training with systems and hardware optimization significantly reduced generation time while maintaining quality. That speed has enabled experiments with continuous video, including streams that can remember previous scenes and respond to new directions…

    Watch on YouTube ↗

The summary and quote tags on this profile are produced with AI assistance from verified, first-person interview transcripts, then checked by our team to confirm the speaker's identity and the accuracy of every quote. See how we verify →