498
Motherboard sales are now collapsing amid unprecedented shortages fueled by AI
(www.tomshardware.com)
This is a most excellent place for technology news and articles.
AI is an amazing tool for fascists.
Annihilate private access to computing, censor and rewrite all comms, destroy free software and the last remnants of education...
Every single decision made for evil.
And all these vendors who are locking themselves into one customer are about to learn why that's a bad idea.
AI is used as propaganda tools to spread it, and it can bee seen on youtube, social media quite readily. plus it sexualizes victims to like csam, and festishized unattainable "women" for conservatives.
conservaties pretty much buys into/believes in anything that is scammy.
The worst thing is that when used for good AI is fantastic! Scientific progress with purpose built AI to find planets, predict the weather, and tons of pattern matching has been in use for decades with positive benefits!
Even LLMs can be a useful tool in the right situations where looking like words people would say but accuracy is NOT important.
The problem is trying to use LLMs to do everything and failing while running the tech industry, the environment, and soon the economy into the ground. They took something positive, ruined it and coopted the terminology while shoving it down everyone's throats.
How are they about to learn why that's a bad idea? Like, when the bubble pops?
I think. Most likely they going to be outcompeted by china.
https://www.bloomberg.com/news/articles/2026-04-27/why-china-s-deepseek-qwen-and-moonshot-are-a-worry-for-us-ai-rivals
This article talks exactly about that: https://tante.cc/2026/04/21/ai-as-a-fascist-artifact/
I don't know if spending unfathomable amounts of money buying up the entire global supply of computing products can be considered a "tool".
I'm not here to argue for or against LLMs in general, but self-hostable AI is a thing. Actually open AI is a thing.
A blanket statement saying about AI as a whole technology being good for fascism is about as useful as saying "roads are good for fascism" (they're great for troop movement after all).
You can't self host anything when the hardware is no longer affordable.
Self hosting an llm ain't the same thing as self hosting nextcloud for your docs and calendar. Yes there are small models but their output is laughable
Small models are improving and becoming more capable. The quality of local LLMs is basically unbounded. The context size of local LLMs is bounded by hardware. So local LLMs can be very capable for small, self-contained tasks.
qwen 3.6 35b running locally:
Single shot. No tool/internet use, so it didn't pull this script from elsewhere.
Output:
I tried to keep the size and scope within something that would reasonably fit in a comment. Looks pretty decent to me, but I can't write Python myself. Never learned. I double-checked the LAT & LON of Miami, and it's spot on.
It did take 47 seconds, while a cloud LLM would probably take 5 or less.
All I'm saying is local LLM isn't garbage and it is getting better all the time.
How much ram and what gpu do you have?
https://lemmy.zip/comment/26338870
Now show the output for an 8b model. The only one I'm capable of running
Gemma 4 e2b is pretty impressive for its size.
This area of computer is improving very fast. I truely belive the future of this is locally installed open models
qwen 3.6 is awesome, but 48-64gb is still real money these days. (though 32gb on dedicated separate machine is also more money). Sonnet 3.5 to opus 4.5 level benchmarks. and the online cost metrics for 27b and 35b are way off considering the overall usefulness of a 48-64gb machine (inclusive of gpu vram for 35b) which even in single, non batching, use could displace $5-$7/day of use.
Local costs are much lower than online costs in linked chart, but if online, there are better models
Depends on if you even need a better model though. Can you run a good enough model is what matters for the most part.
That's interesting.
How much ram did it use while running?
If you used a GPU, how much does it cost in today's prices?
It's a MacBook Pro. 36GB of ram. I am sure Macs have some kind of gpu and I understand it somehow combines GPU ram with system ram, but I don't really know Mac hardware very well.
It's beefy for a laptop, but the desktop I built for myself several years ago had 32 GB of ram and a GTX 1660, so I'm guessing they are similar in capability. I gave that to my daughter, so I can't run a comparison right now.
EDIT: After doing just a bit of research, I've learned the unified memory architecture that Macs use, while not ideal for many purposes, is actually a big advantage for running larger inference models. So it's possible that this particular model wouldn't run at all on my Linux box or would run much slower because the full model wouldn't fit in the 6GB of VRAM and create a lot of memory thrashing.
Yup, you want memory accessible to the GPU for local AI. AMD Strix Point and Mac devices are popular options. CPU can run LLMs but very slowly. I've got 32 GB of RAM and 8 VRAM and it's borderline useless for models that don't fit in the VRAM.
You can use something like KoboldCPP on Linux, which allows both RAM and VRAM combined to run a model. O'course, not as fast when compared to pure VRAM or the Mac approach, but it is an option. I use my 128gb RAM with some GPUs for running models.
Ollama and llama.cpp allow it too but it's super slow in my experience.
decent performance on 6gb gpu without quantization: https://www.youtube.com/watch?v=8F_5pdcD3HY&t=9s
Or available. Companies have pre-sold years worth of inventory to AI companies.
You see hot that's tangential to what you're replying to?
Your point is completely valid, but in another discussion.
Sorry, but I think the point about local AI not necessarily being evil is the tangent here.
The OP is about motherboard shortages, which is being driven by the big AI companies and is making hardware unaffordable for normal users
The top level reply to that is about how that's bad because it removes the ability for people to be in control of their own computing
Then someone comes in, saying "yeah, but you can host your own AI so that it's not evil so not all AI is bad"
Then someone points out that you can only host your AI if you can afford the hardware to do so which, as the OP and the comment you replied to pointed out, is getting really hard to do.
Only when you ignore what was literally the first premise and conclusion.
if you did not understand the comment from above it's fine but splitting hairs like you are doing is silly (everybody knows it's not 100 % of AI is 100% evil)...
your comment is exactly the same as when people say "guns don't kill people, people kill people"... yes, we all know guns are not autonomously killing people, the point is that guns, as a tool, are remarkably good at doing something we do not want, which is to kill people
Not to go on a separate tangent, but that's the entire point of guns. They are supposed to kill. That's not meant to be some crazy conservative defense of them or opposition to regulating them. Just pointing out something that seems to get lost in conversations.
Correct... so when I tell you "guns DON'T kill people, people kill people" you are right to assume and I am just an idiot trying to jingle keys in front of you to distract you from the fact that guns do in fact kill people.
Corps want to privatize roads and make them all toll roads too
They are succeeding in my area.
Roads were also useful for random citizens and people who happened to be in the area.
LLMs are overwhelmingly more useful to bad actors.
I've looked into self-hosted AI and decided it's not worth the cost - both in terms of hardware and energy - when compared to the relative value to be gotten out of it.
Same, pretty much. It is possible though, which makes LLMs a more democratic technology than, say, nuclear reactors.
The models you can run on consumer hardware are still nowhere near the stuff that runs in corporate data centers. To stick with your metaphor, its like running a little steam engine at home while the big guys get to operate nuclear reactors...
You can get pretty far with a stack of 5090s and llama.cpp with split mode graph (or so I've heard, I've never tried), or AMD's unified memory CPU thing.
It's not as good as data centre grade stuff, but it's not nothing either.
Not the best comparison given the interstate highways systems' history of disproportionately targeting Black and Latino communities.
That's kinda my point. Roads are a useful technology, but they can be used by fascists.