100p! in our recent intelligence per watt (ipw) paper, @JonSaadFalcon & i find that 71.3% of real world chat and reasoning queries can be sh…

100p! in our recent intelligence per watt (ipw) paper, @JonSaadFalcon & i find that 71.3% of real world chat and reasoning queries can be shifted from frontier lms to local lms! link to ipw paper in comments below 👇 Good take My guess is - demand for intelligence is near infinite - but 80% of workloads will be running on 99% cheaper models within 12-18 months - 20% of workloads will still run on latest gen models where IQ maxing is important (scientific breakthroughs, higher level ochestrato…

Source: Clem Delangue (X) | 2026-06-08