- cross-posted to:
- technology
- cross-posted to:
- technology
You must log in or register to comment.
[Turbo button pushing intensifies]
Oh shit, didn’t know that. Used to have it enabled all the time
Claptrap, is that you?
Can’t these also run on Raspberry Pis?
Which is much more powerful than this computer.
A bit more secure too
Probably. It would be worth a try.
It just goes to show that the current LLM/AI hype only exists to sell new hardware.
The manufacturers want to keep us in the RatRace, which is why they keep pushing out inefficient features that nobody wants.
Before anyone gets on their soapbox about GNU/Linux, the big distros are just as bloated as Windows and MacOS!
They have “simplified” their installers for novices to the point where everything, including the kitchen sink is installed.
Wtf are you talking about? Like nothing in this ridiculous rant is true
You can run many models on CPUs - but they suck like this one does. It will run fast but generate terrible results.
And what does “bloat” have to do with literally anything here?
You are free to try and run LLMs on your old hardware. Don’t be surprised when (not if) it takes 4 business days to generate completely nonsensical replies to the most basic prompts.
One of the KPIs for IBM engineers used to be kLOCs or “1000 lines of code”. This encouraged the engineers to write more complicated, obfuscated, inefficient code.
If you cleaned up your code to be more efficient, you were penalised.
While this doesn’t make sense to developers and users, it does make sense to hardware sales staff. The crappier a program runs on the existing hardware, the more incentivised customers are to buy new hardware.
My argument is that by adding technologies branded as “AI” to software platforms that inefficiently consume system resources, software developers don’t actually add anything to the platform. It is just a way for manufacturers to create more eWaste through forced obsolescence.
