veroxii

They are starting to do this. Most new models support function calling and can generate code to come up with math answers etc

And the downloaded ones are never in sync properly.

I’ve seen “fair use policy applies”

5 digit here too: 56k something. I think there are many. It feels a bit like those days and I’ve noticed a lot of GenX people here.

Holy Slashdot batman!

Slashdot had this 20 years ago. So you’re right this is not new.or needing some new technology.

“there is none”. Explained in 10 seconds. Happy weekend!

Because all the Arch consultants were busy posting on the internet.

It is not common at all no. Is your network between the 2 machines wired ethernet or wifi?

You might still not. Make sure to look both ways when crossing the road.

Not VMs but I have way more docker containers. I run most things as containers which keeps the base OS nice and clean and free from dependency hell.

You’re pressing the tab key for auto completion right?

This is extremely cool.

Because of the federated nature of Lemmy many instances might be scanning the same images. I wonder if there might be some way to pool resources that if one instance has already scanned an image some hash of it can be used to identify it and the whole AI model doesn’t need to be rerun.

Still the issue of how do you trust the cache but maybe there’s some way for a trusted entity to maintain this list?