First Principles with Christian Keil Podcast
First Principles with Christian Keil
The Deep View
#3: Extropic: Why Thermodynamic Computing is the Future of AI (PUBLIC DEBUT) - episode of First Principles with Christian Keil podcast

#3: Extropic: Why Thermodynamic Computing is the Future of AI (PUBLIC DEBUT)

1 hour 12 minutes Posted Mar 12, 2024 at 1:39 am.
Episode 3: Extropic is building a new kind of computer – not classical bits, nor quantum qubits, but a secret, more complex third thing. They call it a Thermodynamic Computer, and it might be many orders of magnitude more powerful than even the most powerful supercomputers today. Check out their “litepaper” to learn more: https://www.extropic.ai/future.======
- Intro
- Guillaume's Background
- Trevor's Background
- What is Extropic Building? High-Level Explanation
- Frustrations with Quantum Computing and Noise
- Scaling Digital Computers and Thermal Noise Challenges
- How Digital Computers Run Sampling Algorithms Inefficiently
- Limitations of Gaussian Distributions in ML
- Why GPUs are Good at Deep Learning but Not Sampling
- Extropic's Approach: Harnessing Noise with Thermodynamic Computers
- Bounding the Noise: Not Too Noisy, Not Too Pristine
- How Thermodynamic Computers Work: Inputs, Parameters, Outputs
- No Quantum Coherence in Thermodynamic Computers
- Gaining Confidence in the Idea Over Time
- Using Superconductors and Scaling to Silicon
- Thermodynamic Computing vs Neuromorphic Computing
- Disrupting Computing and AI from First Principles
- Early Applications in Low Data, Probabilistic Domains
- Vast Potential for New Devices and Algorithms in AI's Early Days
- Building the Next S-Curve to Extend Moore's Law for AI
- The Meaning and Purpose Behind Extropic's Mission
- Call for Talented Builders to Join Extropic
- Putting Ideas Out There and Creating Value for the Universe
0:00
1:12:59
Download MP3
Show notes
Episode 3: Extropic is building a new kind of computer – not classical bits, nor quantum qubits, but a secret, more complex third thing. They call it a Thermodynamic Computer, and it might be many orders of magnitude more powerful than even the most powerful supercomputers today. Check out their “litepaper” to learn more: https://www.extropic.ai/future.======(00:00) - Intro(00:41) - Guillaume's Background(02:40) - Trevor's Background(04:02) - What is Extropic Building? High-Level Explanation(07:07) - Frustrations with Quantum Computing and Noise(10:08) - Scaling Digital Computers and Thermal Noise Challenges(13:20) - How Digital Computers Run Sampling Algorithms Inefficiently(17:27) - Limitations of Gaussian Distributions in ML(20:12) - Why GPUs are Good at Deep Learning but Not Sampling(23:05) - Extropic's Approach: Harnessing Noise with Thermodynamic Computers(28:37) - Bounding the Noise: Not Too Noisy, Not Too Pristine(31:10) - How Thermodynamic Computers Work: Inputs, Parameters, Outputs(37:14) - No Quantum Coherence in Thermodynamic Computers(41:37) - Gaining Confidence in the Idea Over Time(44:49) - Using Superconductors and Scaling to Silicon(47:53) - Thermodynamic Computing vs Neuromorphic Computing(50:51) - Disrupting Computing and AI from First Principles(52:52) - Early Applications in Low Data, Probabilistic Domains(54:49) - Vast Potential for New Devices and Algorithms in AI's Early Days(57:22) - Building the Next S-Curve to Extend Moore's Law for AI(59:34) - The Meaning and Purpose Behind Extropic's Mission(01:04:54) - Call for Talented Builders to Join Extropic(01:09:34) - Putting Ideas Out There and Creating Value for the Universe(01:11:35) - Conclusion and Wrap-Up======Links:Christian Keil – https://twitter.com/pronounced_kyleGuillaume Verd - https://twitter.com/GillVerdBeff Jezos - https://twitter.com/BasedBeffJezosTrevor McCourt - https://twitter.com/trevormccrt1First Principles:Gaussian Distribution: https://en.wikipedia.org/wiki/Normal_distributionEnergy-Based Models: https://en.wikipedia.org/wiki/Energy-based_modelShannon’s Theorem: https://en.wikipedia.org/wiki/Noisy-channel_coding_theorem======Production and marketing by The Deep View (https://thedeepview.co). For inquiries about sponsoring the podcast, email [email protected]======Checkout the video version here → http://tinyurl.com/4fh497n9🔔 Follow to stay updated with new uploads