Yes, all across Europe there’s no other joking topic other than the political system of Germany.

Rest of Europe, this is what Germans think humor is.

Hundreds? I’m sure he’ll step down right away…

That’s the definition of every piece of software and media ever.

Even the newest Pis use around 2W on idle (which seeding torrents basically is). I’d say the whole setup would be under 10W, or under 5W if the disk is 2.5".

Probably because the ISP is getting paid

Yeah, modern arm CPUs can run at 3GHz and play PS4 level games, but I don’t want my phone to become a handwarmer every time I want to typefvvn a quick email…

And of course, I’m not talking about correcting “fuck” to “duck”, I’m talking about ChatGPT level prediction. Or llama2, or gemini nano, or whatever…

It can and it will. That is one of the uses of “NPUs” I’m most excited about.

Basically you can run an (potentially open-source) small LLM on the phone using whatever context the keyboard has access to (at a minumim, what you’ve typed so far) and have the keyboard generate the next token(s).

Since this is comptationally intensive the model has to be small and you need dedicated hardware to optimize it, otherwise you would need a 500W GPU like the big players. You can do it for 0.5W locally. Of course, adjust your expectations accordingly.

I don’t know any project doing it right now, but I imagine that Microsoft will integrate in SwiftKey soon, with open source projects to follow.

I must have joined after they left, what was it? I’m just familiar with hexbear.