But it only does 16x16 matrix inversion.
Alexstarfire@lemmy.world 1 day ago
It uses 1% of the energy but is still 1000x faster than our current fastest cards? Yea, I’m calling bullshit. It’s either a one off, bullshit, or the next industrial revolution.
TheBlackLounge@lemmy.zip 1 day ago
kalkulat@lemmy.world 1 day ago
Oh noes, how could that -possibly- scale?
TheBlackLounge@lemmy.zip 21 hours ago
To a billion parameter matrix inverter? Probably not too hard, maybe not at those speeds.
To a GPU, or even just the functions used in GenAI? We don’t even know if those are possible with analog computers to begin with.
fcalva@cyberplace.social 13 hours ago
@TheBlackLounge @kalkulat LLM inference is definitely theoretically possible on analog chips. They just may not scale :v
SnotFlickerman@lemmy.blahaj.zone 1 day ago
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:
en.wikipedia.org/wiki/Nature_(journal)#Retraction…
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.
Cethin@lemmy.zip 16 hours ago
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.
DragonTypeWyvern@midwest.social 1 day ago
It’s a weird damn lie if it is.
turdcollector69@lemmy.world 1 day ago
As someone with a 401k I really hope it isn’t.
The economy crashing won’t hurt billionaires but will kill the middle class.
If anything the economy crashing will allow the 0.1% to buy up anything they haven’t gotten already.
actionjbone@sh.itjust.works 1 day ago
And now you see why they want to crash the economy.
tortina_original@lemmy.world 1 day ago
What middle class? 🤔
Zorque@lemmy.world 1 day ago
The one so worried about their 401Ks they won’t risk the ire of the rich.
BreakerSwitch@lemmy.world 16 hours ago
Yeah this is literally what happened in 2008. Economic instability stopped banks from lending to would be individual home buyers, but corpos bought up everything they could eagerly with a 20% price cut.
MajorasTerribleFate@lemmy.zip 15 hours ago
Economic instability is generally better for the people who can weather the storm, i.e. those with resources to spare, because (as you say) they can buy assets on the cheap when the less fortunate run out of cash to survive on and have to liquidate.
It’s long periods of stability that seem to let the lower classes build up a little. Yet another reason why war and strife is of benefit to the rich.
Tollana1234567@lemmy.today 1 day ago
coming from china, more like 1 -off bs, with nothing to backup on.
yoyoyopo5@lemmy.world 18 hours ago
They’re real, but they aren’t general purpose and lack precision. It’s just analog.
CosmoNova@lemmy.world 1 day ago
I mean it‘s like the 10th time I‘m reading about THE breakthrough in Chinese chip production on Lemmy so lets just say I‘m not holding my breath LoL.
4am@lemmy.zip 1 day ago
Yeah it’s like reading about North American battery science. Like yeah ok cool, see you in 30 years when you’re maybe production ready