top of page
newbits.ai logo – your guide to AI Solutions with user reviews, collaboration at AI Hub, and AI Ed learning with the 'From Bits to Breakthroughs' podcast series for all levels.

👉 Subscribe to NewBits Digest

⚛️ Extropic Thermodynamic Chips — 10,000x Energy Breakthrough?

Extropic logo featured in NewBits Digest article on Extropic thermodynamic chips, highlighting the company’s energy-efficient AI hardware breakthrough.

The Big Reveal


Extropic has introduced a completely new class of hardware called Thermodynamic Sampling Units (TSUs) — chips that calculate probabilities instead of instructions. The startup claims this architecture could, in theory, run AI models using up to 10,000× less energy than today’s GPUs, based on early simulations and prototype testing.


This milestone in Extropic thermodynamic chips signals a radical rethink of how computation and physics might converge.


🔬 How Extropic Thermodynamic Chips Work


  • Traditional GPUs compute step-by-step.


  • Extropic’s TSUs skip that grind — they generate probable outcomes directly, similar to how nature optimizes through entropy.


  • The trade-off: less numerical precision, but massive gains in energy efficiency.


⚙️ In essence, it’s analog physics meeting AI math — hardware that thinks in probabilities instead of bits.


🚀 What’s Happening Now


  • Early development kits have shipped to select AI research labs and weather-modeling firms.


  • Open-source tools are live for researchers to experiment with the platform.


  • The company’s first production chip, Z-1, is planned for next year, targeting diffusion models that generate images and videos by denoising across time steps.


🧠 The Vision


Founded by former Google quantum researchers, Extropic believes the AI industry has hit a wall:


“You can’t scale intelligence if you can’t scale energy efficiency.”

Their bet: probabilistic computation could be the next GPU moment — the leap from brute force to elegance.


🌍 Why Extropic Thermodynamic Chips Matter


  • Energy: If the numbers hold, this could slash AI’s global power consumption by several orders of magnitude.


  • Hardware paradigm: TSUs challenge the dominance of GPU-based AI, opening the door to a post-digital, physics-inspired era of computation.


  • Founders: Led by Guillaume Verdon (a.k.a. @BasedBeffJezos on X), the team bridges quantum research and AI innovation.


  • Implication: This isn’t just faster hardware — it’s a philosophical shift toward computing like nature itself.


🌌 The Takeaway


Extropic’s TSUs could mark the beginning of a new era in AI hardware — where intelligence isn’t computed, it emerges.


Whether it’s the dawn of a new physics-based paradigm or the boldest experiment in chip design, the world just got a glimpse of what might come after GPUs.



Enjoyed this article?


Stay ahead of the curve by subscribing to NewBits Digest, our weekly newsletter featuring curated AI stories, insights, and original content—from foundational concepts to the bleeding edge.


👉 Register or Login at newbits.ai to like, comment, and join the conversation.


Want to explore more?


  • AI Solutions Directory: Discover AI models, tools & platforms.

  • AI Ed: Learn through our podcast series, From Bits to Breakthroughs.

  • AI Hub: Engage across our community and social platforms.


Follow us for daily drops, videos, and updates:


And remember, “It’s all about the bits…especially the new bits.”

bottom of page