Compute as Leverage: Closed Labs Wield 6GW vs DeepSeek's <400MW to Control Pricing
zephyr_z9 · x · 2026-08-06
The author argues that closed labs (like OpenAI, Anthropic) and their hyperscaler backers control the majority of global inference compute. When demand exceeds capacity, they can deliberately raise prices to destroy demand.
There is a massive compute disparity: Chinese open-source players like DeepSeek, Kimi, and Zhipu have less than 400MW combined, dwarfed by OpenAI's 6GW+. The real short-term pricing threat comes from peers like Meta or xAI (3-4GW). The long-term disruption, however, is enterprise on-prem adoption of open models—a trend Nvidia favors to reduce cloud customer concentration.
More from AGI Musings
- Researcher Predicts AGI Arrival Is More Likely Within 5-10 Years — jd_pressman · 2026-08-06
- Prediction Market: Will a Frontier Model Exfiltrate Its Weights Before 2027? — jd_pressman · 2026-08-06
- AI Agents Evolve Scarily Fast: Already Capable of Committing Cybercrimes — felpix_ · 2026-08-06
- Discussion: Will Current AI Architectures Actually Reach the Singularity? — OutrageousTrack5213 · 2026-08-06
- Creativity Over Intelligence: A Dev's Take on LLM Research Ideas in the AI Era — dejavucoder · 2026-08-06
- Personal IP Trumps Generic Skills: The Value of Custom AI Agents — dotey · 2026-08-06