China solves 'century-old problem' with new analog chip that is 1,000 times faster than high-end Nvidia GPUs

https://www.nature.com/articles/s41928-025-01477-0

Here's the paper published in Nature.

However, it's worth noting that Nature has had to retract studies before:

https://en.wikipedia.org/wiki/Nature_(journal)#Retractions

From 2000 to 2001, a series of five fraudulent papers by Jan Hendrik Schön was published in Nature. The papers, about semiconductors, were revealed to contain falsified data and other scientific fraud. In 2003, Nature retracted the papers. The Schön scandal was not limited to Nature; other prominent journals, such as Science and Physical Review, also retracted papers by Schön.

Not saying that we shouldn't trust anything published in scientific journals, but yes, we should wait until more studies that replicate these results exist before jumping to conclusions.

I would imagine there's a kernel of truth to it. It's probably correct, but for one rarely used operation, or something like that. It's not a total revolution. It's something that could be included to speed up a very particular task. Like GPUs are much better at matrix math than the CPU, so we often have that in addition to the CPU, which can handle all tasks, but isn't as fast for those particular ones.

coming from china, more like 1 -off bs, with nothing to backup on.

They’re real, but they aren’t general purpose and lack precision. It’s just analog.

1000x yes!

yes, except the bullshit cancer discoveries are always in Israel, and the bullshit chip designs are in china.

Yes. Please remember to downvote this post and all others that are based on overblown articles from nobody science blogs.

“1000x faster?” Learn to lie better

Analogue computers are indeed capable of doing a task 1000x faster than a regular computer. The difference is they do only that task, in a very specific way, and with one specific type of output. You can 3D print at home an "analogue computer" that can solve calculus equations, it can technically be faster than a CPU, but that's the only thing it can do, it's complex, and the output is a drawing on paper.

If you come up with a repeatable and precise set of mechanical movements that are analogous to the problem you want to solve, you can indeed come up with headlines like that.

That and the way companies have been building AI they have been doing so little to optimize compute to instead try to get the research out faster because that's what is expected in this bubble. I'm absolutely fully expecting to see future research finding plenty of ways to optimize these major models.

But also R&D has been entirely focused on digital chips I would not be at all surprised if there were performance and/or efficiency gains to be had in certain workloads by shifting to analog circuits

To be clear though, the two defined states are separated by a voltage gap, so either it is on or off regardless of how on or how off. For example, if the off is 0V and the on is 5V then 4V is neither of those but will be either considered as on. So if it is above thecriticam threshold it is on and therefore represents a 1, otherwise it is a 0.

An analogue computer would be able to use all of the variable voltage range. This means that instead of having a whole bunch of gates working together to represent a number the voltage could be higher or lower. Something that takes 64 bits could be a single voltage. That would mean more processing in the same space and much less actual computation required.

This is an analog pc: https://en.wikipedia.org/wiki/Analog_computer

https://en.wikipedia.org/wiki/Vacuum-tube_computer

It does seem to be talking about this, analog doesn't from my understanding use 1 or 0 as a representation. It is true that the cpu uses voltage as you stated, but what differentiates it from analog is that in analog the volatge isn't represented as 0 or 1 and is used as is in calculations.

They are not programmed, they are physically made to preform the calculation from my understanding, like for example the https://en.wikipedia.org/wiki/Antikythera_mechanism

Digital systems are built on analog systems, as you observed. A continuous voltage range is reduced to two possible states: high voltage (the upper part of that range) and low voltage (the lower part of that range). Then, we design algorithms that manipulate these high/low voltages that only consider the two possibilities of either being high or low. Since we dont consider what the actual voltages are, just if they are high or low, we are doing digital computing, we are not taking full advantage of the analog potential of the physical objects we are using underneath the sheets.

Normal one and zero transistors can hold their state for a while only needing refresh cycles at intervals.
Seems logical to me that it's harder to hold values of greater variance, which is probably also why everything works with binary systems, and not a single vendor has chips that use bits with for instance 3 or 4 states.
What would be most obvious if this wasn't a problem would be to make a decimal based computer. There's a reason we don't have that, except by using 4 bits wasting 6 values, which is very wasteful.

Which is worse - AI slop, or people decrying everything they see as AI slop, even when it isn't?

Ya but they just deported all the employees, probably

West Taiwan. Because The Great Ruling Party said so.

it would need to drop a lot more than 10%

I appreciate that you wanted to help people even if it didn't land how you intended. :)

It was a decent summary, I was replying when you pulled it. Analog has its strengths (the first computers were analog, but electronics was much cruder 70 years ago) and it is def. a better fit for neural nets. Bound to happen.

Nice thorough commentary. The LiveScience article did a better job of describing it for people with no background in this stuff.

The original computers were analog. They were fast, but electronics was -so crude- at the time, it had to evolve a lot ... and has in the last half-century.