ReCoN-thermo PoC integrates probabilistic neural networks with Extropic stack

beffjezos · x · 2026-08-25

MancerAI built ReCoN-thermo, a proof-of-concept integrating ReCoN's continuous probabilistic activations with Extropic's software stack. The CartPole demo visualizes a closed-loop controller, network activations, and state machine states. Currently validated via Extropic CPU jobs and the Torx simulator without thermal silicon, no hardware performance claims are made yet. The next step involves running the probabilistic kernel on actual thermoputer hardware to benchmark time, cost, and energy. Extropic notes that developers can use GPUs (XTR-0) or their Emulators API to explore thermo algorithms now, with the first Z1 cluster expected next year.

Original post →

More from Research

Research channel →