I feel like this article is too cute. The internet, and the state of the art of computing in general has been driven by one thing and one thing alone: Moore’s Law. In that very real sense, it means that the semiconductor and perhaps more generally even just TSMC is responsible for the rise of the internet and the success of it.

We’re at the end of Moore’s Law, it’s pretty reasonable to assume. 3nm M5 chips means there are—what—a few hundred silicon atoms per transistor? We’re an order of magnitude away from .2 nm which is the diameter of a single silicon atom.

My point is, 30 years have passed since dial up. That’s a lot of time to have exponentially increasing returns.

There’s a lot of implicit assumption that “it’s just possible” to have a Moore’s Law for the very concept of intelligence. I think that’s kinda silly.

▲

leptons 2 days ago | parent [-]

Moore's law has very little to do with the physical size of a single transistor. It postulates that the speed and capability of computers will double every few years. Miniaturization is one way to get that increase, but there are other ways.

>The internet, and the state of the art of computing in general has been driven by one thing and one thing alone: Moore’s Law.

You're wrong here... the one thing driving the internet and start of the art computing is money. Period. It wouldn't matter if Moore never existed, and his law was never a thing, money would still be driving technology to improve.

▲

gnarlouse 2 days ago | parent [-]

> The one thing driving the internet and state of the art computing is money

You're kind of separating yin from yang and pretending that one begot the other. The reason so much money flooded into chip fab was because compute is one of the few technologies (the only technology?) with recursive self improvement properties. Smaller chip fab leads to more compute, which enabled smaller chip fabs though research modeling. Sure: and it's all because humans want to do business faster. But TSMC literally made chips the business and proved out the pure play foundry business model.

> Even if Moore's Law was never a thing

Then arguably in that universe, we would have eventually hit a ceiling, which is precisely the point I'm trying to make against the article: it's a little silly to assume there's an infinite frontier of exponential improvement available just because that was the prior trend.

> Moore's Law has very little to do with the physical size of a single transistor

I mean it has everything to do with the physical size of a single transistor, precisely because of that recursive self improvement phenomenon. In a universe where moore's law doesn't exist, in 2025 we wouldn't be on 3nm production dies, and compute scale would have capped off decades ago. Or perhaps even a lot of other weird physical things would probably be different, like maybe macroscopic quantum phenomena or just an entire universe that is one sentient blob made from the chemical composition of cheeto dust.

▲

leptons 2 days ago | parent [-]

Transistor size is not the only metric that matters in computer speed. Maybe you weren't around when 1MHz CPUs were considered fast. Then there were 8Mhz, then 16MHz, then 25MHz, and soon enough it was 250Mhz, then it jumped up to 1GHz, and now we're seeing 4GHz and faster. We're probably not at the end of the GHz that can be achieved. Chip dies got bigger, too. Way bigger. It doesn't matter if a single transistor can't be shrunk smaller than 3nm if the chip size can be increased. We've seen this in Cerebras Wafer Scale Engine (WSE), which is 12 inches by 12 inches and contains 4 trillion transistors. And then there's the possibility of 3D chip design - if you can't go wider, build taller - but the main problem with all of this is heat and power. More transistors, more GHz, larger dies, all means more heat - and heat is the real limiting factor. If heat and power weren't a concern then we'd have far faster computers.

But all of these advancements in processing power are driven by money, not by some made-up "law" that sounds nice on paper but has little to do with the real world. Sorry but "Moore's law" isn't really a "law" in any way like the laws of physics.

▲

gnarlouse 2 days ago | parent [-]

You’ve completely ignored my arguments, you’re hung up on one technicality, and now you’re just being derisive. I literally have a degree in computer engineering. I’m well aware there’s more than just semiconductor size. I’m aware of 3D chip fabs. I’m well aware of clock speed as a dimension. I’m also well fucking aware that moore’s law is not a physical law.

My whole fucking point is that neither are the AI scaling laws.

Please stop talking to me.

	▲	leptons 2 days ago \| parent [-]
		>The internet, and the state of the art of computing in general has been driven by one thing and one thing alone: Moore’s Law Your original comment was downvoted quite a bit. Because you're wrong about this statement, and it sticks out more than anything else you wrote. >Please stop talking to me. Likewise.