

I love how these scenarios never explain the hardware side. How can a software become infinitely smart without infinite hardware?


I love how these scenarios never explain the hardware side. How can a software become infinitely smart without infinite hardware?


Didn’t he take up some fighting sport? maybe that’s a consequence


Eh, better than it coming from data centers


In case, like me, you’re wondering what umu is:
This is a unified launcher for Windows games on Linux. It is essentially a copy of the Steam Runtime Tools and Steam Linux Runtime that Valve uses for Proton, with some modifications made so that it can be used outside of Steam.


“That might come back to bite you”


Yeah I was lucky to buy a 6900XT when it was near the lowest price, so I sold that and added a couple hundred for the 7900, seemed like a good future-proofing move, given the times we’re living in.
I think Apple silicon is faster than my generation of Ryzen, but the newest (Strix something?) with the LPDDRGGFASEWARGH5 memory should be faster yet. Of course buying all that memory right now would be quite painful.


So I have a framework laptop with ryzen ai cpu that uses 48gb of shared ram, and it does run Q4 llms fine enough, but I’m not sure it compares to a real GPU.
On my desktop I have an RX 7900 XTX but I’ve only dabbled in image generation so far, so right now I couldn’t really tell you the difference.


Well it works anyway even with a bit of occupied vram, but you could also buy a cheap videocard to use as an output. I have small intel card like that in my server for jellyfin transcoding, I think I paid 60€ for it, it hardly uses any power
Why yes debian?
I’ve been using it for years and it’s the only one I feel I can safely recommend.
Sad that it’s owned by IBM now.


If your MB has onboard graphics, maybe you could mask the GPU and just pass it off to a container running the LLMs I guess


Yeah, I’m glad I took the time to set up a separate VLAN for this. It wasn’t easy on my MikroTik router (nothing ever is with those), but it’s worth the effort.


it has to share VRAM with the DE. Maybe I’ll set it up for remote development from my laptop instead to free up VRAM.
eh, just systemctl isolate multi-user.target
What a great software
I still have my black Core 2 duo Black Macbook, it’s cut to a 4th of its size, a magnet is stuck near the lid sensor and it outputs video from the port on the side.
I mean it used to output, I haven’t tried turning it on in like a decade
I used to work with a guy who was addressed exclusively by his nickname. Sometimes I wonder if his work contract sported his name or nickname.
Funnily he was one of our union reps in the company, one day we had a big assembly with a couple of union officials, at the end the officials thank each of our three reps: “ok, so thanks to [name], [surname], [name], [surname], and… [guy’s nickname], sorry I don’t know your actual name.”
He now has a fancier PC, courtesy of LTT.

Might be nice if you’re used to it


I have a raidz5 array of 8tb drives, one died, replaced it with no issues
Brexit has shown us that a change of this magnitude should require an absolute majority (66%+)