YC-Backed Dipole Labs Uses Optical Switches to Solve AI Compute Idle Time
ycombinator · x · 2026-08-14
Y Combinator-backed startup Dipole Labs is developing high-speed optical circuit switches to solve the issue of expensive AI compute sitting idle while waiting for data.
The most expensive computers ever built currently spend half their time waiting for data. Dipole Labs' photonic hardware keeps data as light, moving past the physical limits of conventional silicon. At gigawatt scale, this optical layer could recover up to $1 billion worth of compute annually.
More from Infra
- NVIDIA's NeMo Switchyard: Model Routing as the Agent Budget Manager — krishnan · 2026-08-14
- Running MiniMax H3 on RTX 5060 Ti: Resolution is the Real Bottleneck — danielcar · 2026-08-14
- RTX Pro 6000 Price Hikes: Buy a Workstation, Get the Rest for Free — Mr_Moonsilver · 2026-08-14
- NVIDIA Sol Engine Accelerates LTX-2.5 Video Generation by up to 4.68x — gan_chuang · 2026-08-14
- Running 2.4T Qwen3.8 Model on RTX 5090 + 5060 Ti: 0.8 tok/s Tested — mossy_troll_84 · 2026-08-14
- Cerebras and Cisco Shares Plunge Despite Strong Earnings Amid AI Supply Chain Bottlenecks — TiernanRayTech · 2026-08-14