Altman once said open-sourcing was to offload OpenAI's servers—now he calls local inference wasteful
TheZachMueller · x · 2026-10-30
A resurfaced quote from an HF x OpenAI meeting 1.5 years ago shows Altman saying they wanted to open-source models to "offload it from our servers." Now he argues local inference is "a terrible allocation of scarce resources," saying idle home DRAM should sit in the cloud for maximum utilization—a notable reversal in OpenAI's stance on open models.
Related event: Altman calls local inference a poor use of scarce DRAM, sparking backlash(12 posts)→
More from Infra
- Situational Awareness is raising money for neocloud startup Fluidstack, months after near-collapse — nmasc_ · 2026-10-30
- 16GB GPU bandwidth-per-dollar tier list puts RX 6800 on top — HankYeomans · 2026-10-30
- First true omni model runs fully in-browser: 280 tok/s with WebGPU — victormustar · 2026-10-30
- Ben Bajarin: 85% of global IT spend is still on-premises — a 10-20 year cloud flip cycle ahead — BenBajarin · 2026-10-30
- Claude Duet says it runs on Xeon, Dot on EPYC — Ben Bajarin asks if the backends are fungible — BenBajarin · 2026-10-30
- DCOCO paper: contextual correction makes parallel speculative decoding up to 6.6x faster — burny_tech · 2026-10-30