←
Extropic163 posts
Extropic avatar

Extropic

@extropic

building the ultimate substrate for intelligence

◷ Joined July 2023▧ 39 Photos and videos
Extropic avatar
Extropic@extropic·Sep 4

Introducing Z1T: Our first family of transformer-like models made for sparse probabilistic hardware like Z1 Achieving up to 140x energy efficiency gains over GPUs and revealing a new scaling law for sparse transformers Read the blog: extropic.ai/writing/z1t

0:51
Beff (e/acc) avatar
⟳ Extropic retweeted
Beff (e/acc)@beffjezos·Oct 7

Disaggregated inference is the future. Great panel with @general_compute discussing their heterogenous compute cloud, the speciation of compute for disaggregated inference, and how thermo compute will fit in the picture More coming soon. Stay tuned 😉

Post attachment
Beff (e/acc) avatar
⟳ Extropic retweeted
Beff (e/acc)@beffjezos·Oct 6

Will be on a panel discussing the future of inference with friends @general_compute today for SF tech week. You won't want to miss it!

Post attachment
Extropic avatar
Extropic@extropic·Oct 1

What evolves together fits together. We’re using RL to post-train models for Thermo AI research, accelerating algorithmic discovery for our new species of computer. The first sparks of Thermo RSI, in collaboration with @PrimeIntellect. extropic.ai/writing/baby-the…

0:36
MTS avatar
⟳ Extropic retweeted
MTS@MTSlive·Sep 5

Extropic founder @beffjezos explains how Z1 chips sitting alongside GPUs could make AI data centers 100X more energy efficient: "The reason this hasn't been really explored is that there's not a huge upside for sparsity on traditional accelerators. Because GPUs aren't really good if you try to do matmuls that are sparse." "It's like shipping a big freight ship across the ocean with a bunch of empty containers. You're wasting a lot of gas. Whereas for us it's compute and memory, it's naturally sparse. We get a huge energy efficiency gain there" "Nowadays everybody's obsessed with tokens per watt at a data center level. If you incorporate TSUs like Z1 into your data center and park them next to your GPUs, you can get 100X energy efficiency gain at a data center level." "People are struggling to power these data centers. It's become the bottleneck. There's a bunch of GPUs sitting on the sidelines right now that can't be powered on, and people are thinking of creating a Dyson swarm to get more power. Why don't we just compute more efficiently first?" @extropic

2:01

Introducing Z1T: Our first family of transformer-like models made for sparse probabilistic hardware like Z1 Achieving up to 140x energy efficiency gains over GPUs and revealing a new scaling law for sparse transformers Read the blog: extropic.ai/writing/z1t

0:51
Extropic avatar
Extropic@extropic·Sep 4

ICYMI - our recent launch of Z1

7:40
Gill Verdon avatar
⟳ Extropic retweeted
Gill Verdon@GillVerd·Aug 6

the first demo of thermo robot brains ever?

0:17
MTS avatar
⟳ Extropic retweeted
MTS@MTSlive·Aug 4

Extropic founder @beffjezos explains why his new Z1 chip uses 10,000x fewer transistors than a GPU to run the same AI algorithms: "pbits are not traditional bits that are definitely zero, definitely one. They're oscillating between the two. It's like a light switch dimmer. You ever have it flicker when you're at the edge? It's kind of like that." "It's a fractional bit. I could be like, hey, 20% of the time I'm zero, 80% of the time I'm one. That would be a fractional flip." "The most interesting thing is that you can do all sorts of AI algorithms with about 10,000 times less transistors than if you were to do them digitally." "If you go back to the ancestry of neural networks, they came from something called energy-based models from Hinton." "We can do that specifically with Z1. We have literal Boltzmann machines in the hardware. They're very dense, and they use very few transistors, because each transistor is operating in the regime that would be usually considered janky. It's so low power, it's flipping all the time." @extropic

2:54

Major update from us @extropic Announcing Torx and Thermalizers, basically our version of PyTorch + kernels, but for Thermo hardware Also: Z1 is now taped out and in fabrication! Will be available on 0.5M pbit sticks, and 4M pbit PCIe cards +1 more thing at the end... enjoy!

7:40
Extropic avatar
Extropic@extropic·Aug 4

Thermodynamic Computing: From One to One Billion 0:04 - Intro 1:22 - Recap 2:04 - Torx 3:37 - Thermalizers 4:42 - Hardware 6:45 - API 7:25 - Conclusion

7:40
Extropic avatar
Extropic@extropic·Jul 29

X article version

Extropic @extropic Jul 29 Article Extropic Signs $75 Million LOI with U.S. Dept. of Commerce to Scale and Onshore Thermo Computing Planned CHIPS R&D funding to scale Extropic's Thermodynamic Sampling Units for AI workloads and fabricate them at an American foundry. SAN FRANCISCO and WALTHAM, MA — July 29, 2026 — Extropic, the