a16z podcast: fal on real-time video generation, H3 Max, and why control beats speed
a16z Podcast · rss · 2026-09-17
On the a16z podcast, GP Jennifer Li talks with fal co-founder Gorkem Yurtseven and Head of Engineering Batuhan Taskaya. Key points: H3 Max is fal's post-trained version of MiniMax's open-weight video model, combining post-training with systems and hardware optimization to cut generation time while keeping quality. That speed enables continuous video — streams that remember previous scenes and respond to new directions mid-run. They argue the next frontier is control (camera movement, lighting, characters, motion, lip sync) rather than speed, and that professional creative workflows need predictable tools, not one-shot prompt roulette.
More from Infra
- US House Passes Bipartisan Bill Making Data Centers Cover More Grid Costs — Polymarket · 2026-09-17
- Dev trains a 2B Apache-licensed model on 24GB VRAM using OLMo embeddings and a 1B Engram table — NineThreeTilNow · 2026-09-17
- Applied Materials to invest $5bn in India as country boosts chip support — pstAsiatech · 2026-09-17
- Cloud AI Costs 10-20x More Than On-Premises, Expert Warns of Repeat of Early Cloud Mistakes — DavidLinthicum · 2026-09-17
- Huawei says AI chip demand outstrips supply, plans two new AI chips by 2027 — sunychoudhary · 2026-09-17
- 71% of Americans oppose local AI data centers — more than oppose nuclear plants — DavidLinthicum · 2026-09-17