silverlose

I think whats really happening behind the scenes is that the model you’re talking to makes a function call to another model that generates the image.

I haven’t seen it either so if you want that and don’t want to code it might be best to stick with paid, but something like that could easily exist somewhere else.

FWIW speech to text works really well on Apple stuff.

I’m not exactly sure what info you’re looking but: my gaming PC is headless and sits in a closet. I run ollama on that and I connect to it using a client called “ChatBox”. It’s got a gtx 3060 which fits the whole model, so it’s reasonably fast. I’ve tried the 32b model and it does work but slowly.

Honestly, ollama was so easy to setup, if you have any experience with computers I recommend giving it a shot. (Could be a great excuse to get a new gpu 😉)

Very true. I think the tank, much like the cannon, will still have its own niche use case but isn’t the silver bullet so many armies saw it as. Happens a lot I think

Have you heard of ollama? You can run deepseek and stuff locally super easy. I know it’s not a complete replacement, but it feels nice to use an LLM guilt free. I’ve compared the 14b distilled model from deepseek vs the paid version of ChatGPT and it made me cancel my account.

I fucking love that 😆

It’s a trade off for sure. I think the area editors like Vim totally win in is when you need to ssh into a server and edit something. I think it will always exist because of this use case

Maybe. I don’t know what it’s like in Russia at all.

I’m a StarCraft player, which means that I do not need the numkeys and absolutely have a mental disorder. Why do I do this to myself? Mama Mia 😞

Why would he need a reason though? Couldn’t he just do that at any time?

Nice catch!

Awww hell yeah this is amazing news! Thank you

(Also why didn’t I think about mastodon- I’m such an idiot)

Yay! More users for lemmy!

Uh so… does anyone know if Lemmy will scale to millions of users? Has an ActivityPub service ever gotten to that scale?