Free Open-Source Artificial Intelligence

2951 readers

6 users here now

Welcome to Free Open-Source Artificial Intelligence!

We are a community dedicated to forwarding the availability and access to:

Free Open Source Artificial Intelligence (F.O.S.A.I.)

More AI Communities

LLM Leaderboards

Developer Resources

GitHub Projects

GitHub Stars

FOSAI Time Capsule

founded 2 years ago

MODERATORS

Blaed

fosai

AI language model runs on a Windows 98 system with Pentium II and 128MB RAM (www.tomshardware.com)

submitted 4 days ago by cm0002 to c/fosai

12 comments fedilink hide all child comments

top 12 comments

sorted by: hot top controversial new old

[–] [email protected] 7 points 3 days ago (1 children)

[Turbo button pushing intensifies]

[–] Anti_Iridium 2 points 2 days ago (1 children)

https://youtu.be/p2q02Bxtqds

[–] [email protected] 2 points 1 day ago

Oh shit, didn't know that. Used to have it enabled all the time

[–] EmpatheticTeddyBear 6 points 3 days ago

Claptrap, is that you?

[–] [email protected] 2 points 4 days ago (2 children)

Can't these also run on Raspberry Pis?

[–] Alexstarfire 11 points 4 days ago (1 children)

Which is much more powerful than this computer.

[–] [email protected] 3 points 3 days ago

A bit more secure too

[–] [email protected] 1 points 4 days ago

Probably. It would be worth a try.

[+] [email protected] -13 points 3 days ago (2 children)

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.

[–] [email protected] 10 points 3 days ago

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?

[–] herrvogel 4 points 3 days ago (1 children)

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.

[–] [email protected] 2 points 3 days ago

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.