It’s also a massive difference in Canada. With Elegoo, I can get pla for $15 CAD, but prusament is $48 CAD. That’s over triple the price… Thankfully Elegoo filament works great

Yes, it does. Like I have said, that part of the protocol is called MatrixRTC. It is not a hack, or a mod, or third party.

Matrix is a protocol, its all through some other software. Livekit is just a good and easy webrtc server that you can tie in with something like synapse

Join different servers then? Not sure what to tell you.

I use element and I am in many different matrix servers with voice rooms. I host my own as well, voice is done via livekit which makes connecting via MatrixRTC very easy, and is easy to setup and host.

Those same voice rooms support webcams / video, as well as screen sharing.

Matrix has all that these days too

Not talking about caching (though there would be some decent memory savings due to that on general platforms like ChatGPT and tools like Codex). I am talking about large batch sizes, which are concurrent requests all accessing the same memory at the same time. The model is loaded once onto the GPU(s) and then many simultaneous requests can read that memory at the same time. When those requests are all processing their responses simultaneously, the energy per token drops off a cliff.

And yes, running a smaller model would generally take less power, but thats not really a fair comparison. Small models just wont give you the same results as larger ones. You need to compare it apples to apples. If you want to compare your local Qwen model running on your laptop, you compare those numbers to larger systems supplying that same qwen model to thousands of people. Just because we are comparing cloud services to local doesn’t automatically mean GPT 5.6 vs Qwen 3.6 27B. There are plenty of cloud AI providers running all sorts of models and sizes.

As for one of the articles I learned alot of this from originally, this is one I recommend going through. It really goes deep into the whole topic: https://arxiv.org/html/2601.22076v1

Very serious. Your personal amount of usage means nothing at all in this conversation. It is entirely about tokens per watt. The amount of energy the memory operations involve scale incredibly well when people are accessing the same object in memory simultaneously. Last I looked it was around a 10x difference for the same models efficiency.

If you want me to be your personal search engine you’ll need to wait a bit, im making dinner right now and would rather look for the articles on my desktop.

You have that backwards. The only thing you gain from running local models is privacy. It is not cheaper, it is not more efficient. You are actively hurting the environment MORE by using a local model on your own. LLM efficiency sky rockets the more users there are on a single loaded model.

IMO the only way we get to efficient LLM usage would be by having very efficient non frontier models running only for its local community to use, where you can have assurances on whether its power source is clean or not. That doesn’t help with the plagiarism aspect though

Thankfully I have managed to get everyone to switch from Messenger to Signal, atleast for talking to me haha. Two other family members being privacy oriented too really helped getting the rest of the family moved over.

Must be more popular in your country, in Canada I don’t know a single person on whatsapp

uhm, no? Literally none of that was considered AI. Even chatbots, people weren’t calling them AI until LLMs came around and were stuck in them. Lisp is a language USED for AI research, that doesn’t make it AI itself.

This bot is most definitely not even close to what people consider AI

It wasnt even LLMs until the public took the term and changed it lol. Unless you are calling every algorithim ever made AI these days, this isnt AI.

It isn’t AI, you can take a look at the source code for it from the url it provides. Obviously the detection needs some tweaking, but extra acronyms in the list doesn’t really hurt anything when the other half are relevant.

When did you last check? I believe jellyfin apps made it onto tizen OS a few months ago

It is also the most popular game ever created, unfortunately. Just one of the user created games on it tops the list for daily active players of any game ever…

Grey text has always been a hint / tip / example, why would it be an implicit default?

Canada has even worse competition and higher prices than the states lol

My main source of grease and oil is from stuff i cook in my airfryer lol

You might want to go back and read my comment again :)

I would think it’s a very non-american problem, though. They already have super easy access to real guns. It’s all the other countries with gun restrictions that need to worry about printed guns.