What If We Stopped Using GPUs? | YC Paper Club
Episode details
Episode description
This week's Paper Club is all about alternative compute. We cover the case for abandoning backprop and the gradient-free optimizer being built to replace it, how the propagation of light can be programmed to run a diffusion model, where neuromorphic computing really stands in 2026, and how human brain cells on a chip learned to play Doom. Sign up for the next Paper Club, where we'll discuss AI Safety: https://events.ycombinator.com/yc-paperclub-oct7 Chapters: 00:00 — Intro 00:07 — Francois Chaubard: Why Alternative Compute? 03:38 — Beyond Backpropagation 08:08 — Zero-Order Optimization and SOMA 15:06 — Ilker Oguz: Computing With Light 19:27 — Why Optical Computing Isn’t Everywhere Yet 22:23 — Building a Diffusion Model With Light 30:03 — Optical Computing Q&A 39:00 — Alok Vasudev: What Is Neuromorphic Computing? 45:23 — What the Brain Can Teach Us About Chips 49:35 — Where Neuromorphic Computing Stands Today 54:24 — Neuromorphic Computing Q&A 1:04:24 — Sean Cole: Teaching Brain Cells to Play Doom 1:07:48 — Training Biological Neurons With Reinforcement Learning 1:12:28 — How Brain Cells Learn From Feedback 1:15:40 — Biological Computing Q&A Apply to Y Combinator: https://www.ycombinator.com/apply Work at a startup: https://www.ycombinator.com/jobs
AI summary
YC Paper Club explores alternatives to the close relationship between transformers, backpropagation, and GPUs in modern AI. The discussion covers optical systems that compute with light and neuromorphic architectures inspired by the brain. It also examines experiments in teaching living brain cells to play Doom and how biological neurons learn from feedback.
Watch also from the same channel
More episodes from this channel
You might be interested in
