Chutes team on Bittensor Subnet 64 may have stumbled on a new way to train models while fixing inference economics
markjeffrey · x · 2026-10-01
- Chutes (Bittensor Subnet 64) at one point served billions of tokens a day on OpenRouter but was unprofitable; the network's competitive incentives pushed it to serve inference more efficiently.
- While solving that, backend dev @jondurbin and the team may have discovered an entirely new training method that could revolutionize decentralized training and unlock open-source models.
- The full story is told in an attached podcast episode.
More from Infra
- Paraguay's $12B Iguazú AI City to host Latin America's largest data center — teortaxesTex · 2026-10-01
- You.com, NVIDIA and CoreWeave bring live web search into RL training, starting with Nemotron 3.5 Lightning — RichardSocher · 2026-10-01
- Padding trick lets vLLM run tp=6: 27B model at 50 tok/s on six 7900 XTX GPUs — Biomass23 · 2026-10-01
- Ornith-1.5 DFlash draft models deliver up to 2.54x lossless inference speedup — alan_ritter · 2026-10-01
- Manager locked Teams transcripts, employee used Copilot to dig JSON URL out of page source — TheBigCrowbroski · 2026-10-01
- Compute per MW comparison: Nvidia still best price/perf despite prices — Storge2 · 2026-10-01