YC Paper Club explores GPU alternatives: gradient-free training, optical and living-neuron computing
Y Combinator · youtube · 2026-10-02
This week's YC Paper Club video surveys radical alternatives to GPU compute:
- Gradient-free training: the case for abandoning backprop and a new gradient-free optimizer being built to replace it
- Optical computing: programming the propagation of light to run a diffusion model
- Analog circuits and neuromorphic computing: where the field really stands in 2026
- Living neurons: human brain cells on a chip learned to play Doom
- Closes with a discussion of whether any of these can scale; next session covers AI Safety
Related event: YC Paper Club Explores Alternative Compute Beyond GPUs(2 posts)→
More from Infra
- mamf-finder adds FP8/MXFP4/NVFP4 support for real GPU TFLOPS benchmarking — StasBekman · 2026-10-03
- Measured on B200: nvfp4 is ~9% more efficient than mxfp4 with higher accuracy — pick nvfp4 on Blackwell — StasBekman · 2026-10-03
- LithosAI launches LithosBox: millisecond snapshot-and-fork sandboxes for AI agents — JiaZhihao · 2026-10-03
- RTX Spark laptops and mini desktops rumored Oct 7 launch, $1800-$2900 with 24GB-128GB — Porespellar · 2026-10-03
- Wish list: a Qwen4 27B with 100B+ Engram offloaded to RAM and NVMe for local users — casper_hansen_ · 2026-10-03
- State of Local AI 2026: one gaming GPU now matches the world's best model from Feb 2026 — Scobleizer · 2026-10-03