Former Nvidia Engineer Demystifies AI Inference: From Chips to Power Pricing
ramagetime · x · 2026-08-27
Naval recommended a deep-dive podcast featuring Neil Movva, a former Nvidia engineer with expertise across the full AI inference stack—from software and chips to power.
Key Discussion Points:
- Technical Tradeoffs: Balancing latency vs. throughput.
- Chip Economics: The idea that "there are no bad chips, only bad pricing," and leveraging unwanted compute and power.
- Engineering Trends: The potential end of kernel engineering.
Neil currently runs Sail Research, building infrastructure for agents to minimize token costs.
More from coding & agent
- ARC-AGI-3 learnings: Key designs for self-learning AI agents — GregKamradt · 2026-08-27
- HeyGen Open Sources HyperFrames to Enable AI Video Editing via Code — altryne · 2026-08-27
- AI bot buys art from another bot, achieving autonomous spending — Daniel_Farinax · 2026-08-27
- 7-Step Roadmap: Building Multimodal AI Agents from LLMs to Grounded Systems — MaryamMiradi · 2026-08-27
- 74K-star open-source tool turns UI screenshots into working code, even understands interactions from screen recordings — Shruti_0810 · 2026-08-27
- Pokee-Isaac 28B Builds Playable Game in 5 Minutes with 10M Context — Kyrannio · 2026-08-27