Change w/ Jim Keller
Tenstorrent1 HN recommender · recommended in 1 month, 2023–2023
talk · general · evergreen · 2023–2023 on HN
Jim Keller, CTO of Tenstorrent, gives a keynote at Stanford's System X conference on change, understanding and the future of computing. He touches on Moore's Law, how far transistors are from physical limits, and ideas like DNA origami.
HN commenters cite it as a thoughtful talk from a legendary chip architect, both for the s-curves view of progress and for concrete technical details on semiconductor scaling.
Up next
2 mo on HNVibe coding complex changes in Rust
Jon Gjengset
2 HN recommender · 2025–2026
3 mo on HNCppCon 2015: Bjarne Stroustrup “Writing Good C++14”
CppCon
2 HN recommender · 2016–2018
3 mo on HND is for Debacle - The Crucial Story of Vitamin D and Human Health
Ivor Cummins
3 HN recommender · 2017–2020
3 mo on HNWhy Machines That Bend Are Better
Veritasium
3 HN recommender · 2019–2021
4 mo on HN"Performance (Really) Matters" with Emery Berger
Association for Computing Machinery (ACM)
3 HN recommender · 2022–2026
8 mo on HNAnalogy as the Core of Cognition
Stanford
7 HN recommender · 2012–2025
3 mo on HNRobust-first computing: Beyond efficiency
Dave Ackley
3 HN recommender · 2015–2025
1 mo on HNThe Story Behind Audacity
Tantacrul
3 HN recommender · 2021–2023
12 mo on HN8-bit computer update
Ben Eater
14 HN recommender · 2017–2023
11 mo on HNLight Years Ahead | The 1969 Apollo Guidance Computer
TNMoC
11 HN recommender · 2021–2026
11 mo on HN“Hello, world” from scratch on a 6502 — Part 1
Ben Eater
11 HN recommender · 2019–2026
10 mo on HNFinding the Missing Memristor - R. Stanley Williams
The Qualcomm Institute
12 HN recommender · 2010–2024
5 comments from Hacker News
If you are fan of the stack of s-curves, you will probably like this talk by Jim Keller. Jim Keller on Change ▶ this video
Transistor measurements in nanometers has been more or less meaningless since the introduction of FinFETs over a decade ago, and IIRC it was TSMC that started the let's play funny business with nanometers affair. Today they are marketing terms and the different fabs try to align them somewhat, but have inherent conflicts of interest when it comes to overselling their tech. For example a TSMC N5 transistor is roughly 100x100x100nm in size as per ▶ this video .
We are ridiculously far from physical limits in our current artificial computers (both theoretical [1], and practical [2]). For more technical details see Jim Keller: [3] [4] [5]. [1] link [2] The ~12 watts computer inside each living human adult skull (and perhaps each eukaryote cell [6]) is still the state-of-the-art, for quite some time. [3] 2021, Jim Keller: The Secret to Moore's Law , link [4] 2019, Jim Keller: Moore’s Law is Not Dead , link [5] 2023, Change w/ Jim Keller , ▶ this video [6] Our computers aren't yet able of polycomputation, where the computation topology, data, and functions depend on the observer, instead of computation in a passive implementation, once done forever set in s̶t̶o̶n̶e̶ silicon, 2023, Michael Levin, Agency, Attractors, & Observer-Dependent Computation in Biology & Beyond , link
"Is this really the way forward?" No. The way forward for scale-free systems which implement a hierarchy of competence is to have "the factory smaller than the product" [1]. Instead of the Chrome Canary team and the various Working Groups dictating from above what passes as valid, let the rules be sent at the same time with the interpretation of the rules [2]. In the same manner DNA encodes proteins with no mention of the underlying morphology, but once the RNA starts building the morphology arises. [1] Jim Keller talking about DNA Origami at 19:18, ▶ this video [2] Not even such a new idea, "Building a Better Web Browser - James Mickens - Harvard CS Colloquium 2015", on rendering at 04:20, link
K8 seems pretty small after he made the fucking Zen architecture (and Tesla AI). Lex has good interviews with Jim[1], he's not just very smart, he is wise. He started Tenstorrent some time ago with Ljubisa Bajic so I'm assuming this fab is related. Here is youtube channel for Tenstorrent[2], and last time I checked it was getting under 100 views per video... Ian also interviewed him[3] some time ago. Long story short if I had money that would be relevant in this context I would invest really hard into Tenstorrent. Investing time to listen to the guy seems to be not worse. 1a. link 1b. link 2. ▶ this video 3. link