CarbonForge

Using AI to discover more efficient ways to run AI. Optimizing inference across software and hardware for more performance per watt.

[CarbonForge @carbonforgeai]

An agent choosing its own experiments can confirm false findings by peeking, testing many claims, or retrying. When nothing is true, peeking alone gives 43% false supports; EvidenceTree keeps it under 2%. NeurIPS 2026 e-values workshop, by @pierrelux

https://t.co/PE0x2m2QZP

[CarbonForge @carbonforgeai]

LLM decode is often memory-bound, so extra SM clock becomes power, not tokens. A serving-aware clock governor on 2xA100 cut GPU power 12 to 13% at matched capacity, and about 30% on saturated decode. Model and engine untouched. By @pierrelux

https://t.co/6AbC8wPuhA