The Core Ultra chips, like the Ryzen 7040-series chips, also include a neural processing unit (NPU) that can be used to accelerate some AI workloads. But both NPUs fall far short of the performance required for Recall and other locally accelerated AI features coming to Windows 11 24H2 later this year;
Meteor Lake was taped out in May 2021 and launched in December 2023. Still much slower than the pace of LLM development, to be fair. It seems more like an “if you build it, they will come” approach. But that’s also how we got stuck with (for most consumer purposes) useless tensor cores on our GPUs. Does anyone even give a shit about raytracing/DLSS anymore?
I don’t need to outplay humans, I need to see the optimal line to analyze it. Chess is still not solved, so Leela Zero is still helpful because it’s giving better advice than older engines. Even Stockfish went neural network, but a smaller one that reads deeper. They still can’t tell us if the game from the start ends in a draw like checkers.
Killing jobs is good. It’s already freeing people from having to write things like promotional emails. Maybe they are sad they don’t have a job anymore, but unemployment if 4%, hardly difficult to get a different one. It’s not an important job anyway, I wouldn’t feel creative to write about a labor day sale or whatever
Why even waste the fucking space on the die then?
NPUs existed before recall and have other uses apart from that.
Because the NPUs were designed and built and included long before Windows 11’s AI features were announced?
If I recall correctly, it typically takes about 4 years for a CPU to go from design to distribution.
Meteor Lake was taped out in May 2021 and launched in December 2023. Still much slower than the pace of LLM development, to be fair. It seems more like an “if you build it, they will come” approach. But that’s also how we got stuck with (for most consumer purposes) useless tensor cores on our GPUs. Does anyone even give a shit about raytracing/DLSS anymore?
It actually sounds like Microsoft is betraying Intel for Qualcomm, since their upcoming processor in the new Surface tablet is the only one that actually meets the requirements. So it looks like Microsoft doesn’t give two shits about supporting existing hardware either way.
Tensor cores can be used to play chess, generate images, do realistic text to speech, do noise cancellation, content-aware fill, etc.
They are only useless to you and other people with no imagination
Chess engines have outplayed humans for thirty years, and they didn’t need teraflops of computing power to do it.
Generative AI is actively harmful to the environment, slowing the phase-out of coal in the US and guzzling billions of gallons of water. It’s likely going to kill jobs and it’s already filling the internet and the academic world with garbage. It’s also likely a bubble that will burst before long, potentially bringing the economy down with it.
I’ll give you noise cancellation and text-to-speech, that’s pretty cool.
But personally, I’d rather have more CUDA cores.
I don’t need to outplay humans, I need to see the optimal line to analyze it. Chess is still not solved, so Leela Zero is still helpful because it’s giving better advice than older engines. Even Stockfish went neural network, but a smaller one that reads deeper. They still can’t tell us if the game from the start ends in a draw like checkers.
Killing jobs is good. It’s already freeing people from having to write things like promotional emails. Maybe they are sad they don’t have a job anymore, but unemployment if 4%, hardly difficult to get a different one. It’s not an important job anyway, I wouldn’t feel creative to write about a labor day sale or whatever
Now people want recall?
I sure as hell don’t, but it seems extra pointless when it can’t even run the workloads it was designed for.
I’m sure it still works in photoshop or whatever, just not the windows stuff.