Extropic claims 100x-10,000x efficiency in first results on thermodynamic recursive intelligence
beffjezos · x · 2026-10-02
Extropic (founded by Guillaume Verdon, aka beffjezos) published "First Sparks of Thermodynamic Recursive Intelligence" with Prime Intellect, declaring "Wired: Fooming" — recursive self-improvement for power-efficient hardware is just beginning and accelerating.
- Extropic argues for hardware-algorithm co-design: algorithms on its thermodynamic hardware can be 100x–10,000x more efficient than matrix-multiplication approaches on GPUs/TPUs, so inference should be ported ASAP.
- The company frames modern deep learning as 15 years of evolutionary search tuned for matmul accelerators; thermodynamic computing is a different species of hardware needing a new species of algorithms.
- It has open-sourced a thermodynamic programming stack — Torx (high-level programming), Thermalizers (compiler to the thermo hardware fabric), and THRML (low-level sampling framework) — to speed up algorithm discovery.
Related event: Extropic Claims First Breakthrough in Thermodynamic Recursive Intelligence(2 posts)→
More from Infra
- Benchmark Backs Chip Startup Tendrils Compute in Round That Could Top $1B Valuation — Sethwinterroth · 2026-10-02
- Modal Runtime ships multi-node clusters, VM sandboxes and sticky sessions — graceisford · 2026-10-02
- How to run local T2V/I2V/V2V video AI on an RTX 5070 with only 12GB VRAM — AirSea2062 · 2026-10-02
- Nebius Outperforms CoreWeave by 8X Despite 5X Less Revenue: What's Going On — Beth_Kindig · 2026-10-02
- Pedro Domingos: data centers lower electricity rates by paying the same overhead as residents — pmddomingos · 2026-10-02
- PyTorch ships TorchTPU: vLLM and SGLang now run natively on Google TPUs — PyTorch · 2026-10-02