Sam Altman: Local inference is a terrible allocation of scarce global compute
morqon · x · 2026-10-30
Sam Altman pushes back on the idea that open-source models make local inference the future: idly sitting DRAM in everyone's computer, used 5% of the time, is a terrible allocation of a globally scarce resource. In a supply-constrained environment, he argues, you want maximum utilization in the cloud — and many people's intuition is exactly backwards.
Related event: Sam Altman calls personal local inference a poor global use of compute(3 posts)→
More from Infra
- 10 coding agents tested on local Qwen 3.8 27B: Pi wins on efficiency at 9.2k tokens per task — latent_lurker8587 · 2026-10-30
- Banks Shelve $5-7B Junk-Bond Sale for Anthropic-Leased Texas Data Center on Grid Audit — rohanpaul_ai · 2026-10-30
- Weight compression on the GPU: researcher proves his own instinct wrong — realDanFu · 2026-10-30
- Cached tokens explained: agent loops overpay for the same prefix, 50x savings — Arindam_1729 · 2026-10-30
- GB300 NVL72 runs DeepSeek Flash at ~1000 tok/s/user, ~$0.07 per 1M tokens TCO — bookwormengr · 2026-10-30
- Sam Altman: self-replicating AI-built data centers are 'within grasp' — Eliv_nurotic · 2026-10-30