Ushering in the Thermodynamic Future - Litepaper
We are very excited to finally share a bit more about what we are building: a full-stack hardware platform to harness the natural fluctuations of matter as a computational resource for Generative AI.
The demand for computing power in the AI era is increasing at an unprecedented exponential rate. Luckily, for the past several decades, the miniaturization of CMOS transistor technology following Moore’s law [1] has allowed much of this exponential growth to be accounted for by increasing computer efficiency. Unfortunately, Moore’s law is starting to slow down [2]. The reason for this is rooted in fundamental physics: transistors are approaching the atomic scale where effects like thermal noise start to forbid rigid digital operation [3][4][5]. As a result, the energy requirements of…
saved by
- Yufei Xiao
- Svitlana Midianko
- Tazik Sh
- Rajan Agarwal
- Turja Chowdhury
- Hangyul Lyna Kim
- Yoyo Yuan
- Aishwarya Mahesh
- Mackay G
related reading
- Why AGI Will Not Happen - Tim Dettmerstimdettmers.com
- The Moon Should Be a Computerpalladiummag.com
- Researchnormalcomputing.com
- Computational Power and AI - AI Now Instituteainowinstitute.org
- Unconventional AIunconv.ai
- Thermodynamic Computingarxiv.org
- My picture of the present in AI — LessWronglesswrong.com
- As Rocks May Think | Eric Jangevjang.com
- Navigating the High Cost of AI Compute | Andreessen Horowitza16z.com
- Can AI scaling continue through 2030? | Epoch AIepoch.ai
- Dylan Patel — Deep dive on the 3 big bottlenecks to scaling AI computedwarkesh.com
- The Short Case for Nvidia Stock | YouTube Transcript Optimizeryoutubetranscriptoptimizer.com