Sam Altman says local inference is a 'terrible allocation' of scarce DRAM in a supply-constrained world
teropa · x · 2026-10-31
In quoted remarks, Sam Altman argued that local inference is "quite terrible" from a global allocation perspective: the world's limited DRAM supply would sit in personal computers used 5% of the time, while the environment is severely supply-constrained. He says compute should be centralized in the cloud for maximum utilization.
Reposter WBBaskerville countered that this amounts to "people want to own their own property but they shouldn't be allowed to," noting there was no deeper layer to the argument.
More from Infra
- Nvidia weighs cosigning loan for Nscale's West Virginia AI data center — TechCrunch AI · 2026-10-31
- Northflank dunked on Railway's breach, then got hacked the same way 9 days later — aniketmaurya · 2026-10-31
- Dev says Neon is already chasing millisecond infra branching, wants it built into alchemy — samgoodwin89 · 2026-10-31
- Big AI labs all push compute efficiency: Trainium power savings, small models, cache compression — WillfullyWorkable · 2026-10-31
- Running 12 agents on one RTX 3090 lifts total throughput from 30 to 110 tok/s — Mchanger · 2026-10-31
- Analyst turns ultra-bull on Avicena after 6 hours of technical diligence — BenBajarin · 2026-10-31