aiqbench analysis
MIT researchers have developed 2nm nanoscale devices that mimic neuron firing using viscoelastic polymers to store information mechanically, potentially enabling low-power computing architectures. This approach integrates storage and processing within the material itself, addressing adhesion challenges in mechanical computing while offering new pathways for efficient hardware design. The technology represents a significant step toward bio-inspired computing platforms that could power next-generation wearable devices and specialized AI accelerators.
MIT builds nanoscale devices that mimic neuron firing

MIT engineers built devices, 2nm in size, that mimic how neurons fire, potentially enabling more efficient computing.
MIT researchers have built a chip containing hundreds of nanoscale devices, each with a viscoelastic polymer layer measuring just 2 nanometers. These devices mimic neuron firing through reconfigurable motion, potentially leading to more efficient computing platforms. The technology minimizes components by integrating computing functions into the material itself, opening opportunities for low-power applications like wearable health devices. “Complex and coupled nanoscale phenomena can provide tremendous opportunities for new approaches to information processing,” says Farnaz Niroui, an associate professor at MIT and senior author of the research. Featuring a 2-nanometer layer of polydimethylsiloxane (PDMS), a viscoelastic polymer, the core of the new nanoscale devices dictates how they process information through…
Excerpt shown under the publisher's RSS terms · 109 words · full text and figures are on the publisher's site
Related coverage

The Lab Mistake That Might Revolutionize Computing
IEEE Spectrum · Jun 29, 2026
The J-Space Debate, Agent Swarms, and Pacing Frontier AI - Digital Minds Newsletter #4
LessWrong · Sep 18, 2026

Heat Currents Build Nanoscale Circuits Mirroring Electronic Logic Gates
Quantum Zeitgeist · Jun 15, 2026

UC San Diego unlocks quantum control of ‘learning’ & ‘forgetting’ material
Quantum Zeitgeist · Oct 14, 2026