ChipsSeptember 8, 2026via MIT Technology Review
This founder is teaching chips how to recycle (their energy)
Why it matters
As AI data centers consume record power, a startup is commercializing reversible computing to recover energy wasted as heat in silicon. This is foundational hardware innovation that could reshape compute economics and the feasibility of frontier model training.
Key signals
- Hannah Earley, 31, is CTO of Vaire Computing
- Vaire is building chips using reversible computing to recycle waste heat energy
- Reversible computing treats heat dissipation as a design choice rather than an inevitable cost
- The approach has potential to reduce power consumption in AI accelerators and data-center infrastructure
- This is a direct response to AI's exploding power footprint and data-center energy constraints
The hook
Reversible computing could cut AI chip power consumption by orders of magnitude — and Vaire Computing is the first to ship it.
Throughout the history of the computer chip, engineers have treated waste heat as an inevitable cost of a calculation. Hannah Earley, however, thinks it’s a design choice. Earley, 31, is cofounder and chief technology officer of Vaire Computing, a startup building chips that recycle energy usually t…