This seems cool but also a gateway for RSI

You don’t need to run the LLM on the device. It supports 13 different protocols for both text completion and chat completion.

There’s also RisuAI which has some nicer features like better integration with function calling. Sillytavern is working on Function calling more but it’s not quite there yet.

The nice thing about Sillytavern is that it also has plugins for Alltalk for TTS and ComfyUi/A1111 for image generation directly from the roleplay interface.

It also has support for RAG through upload of documents and web scraping and a shitload of other features it would take awhile to list here.

Mostly decking about.

What do you mean by personal package manager?

What do people use for command line utilities? The selection on flatpak is a bit sparse

It depends on whether those dependencies are shared with other programs.

Somebody hit the token chain jackpot

USB-C is pin-compatible with every single other USB plug, so you should be able to get away with all USBC cables and some adapters for whatever plug type you’re trying to plug in.

There are only 3 types of pin sets, USB-C(USB 3.0 pins + 3 extra pins), USB-3.0(USB 1.0 + 5 extra pins) and USB-2.0 and lower. Everything else version wise is the controller on the actual board, not the cable.

Cable-wise you only need one to get the benefit of every other plug on the market.

This isn’t really accurate either. At the moment of generation, an LLM only has context for the input string and the network of text tokens it’s been assigned. It pulls from a “pool” of these tokens based on what it’s already output and the input context, nothing more.

Most LLMs have what are called “Top P”, “Top K” etc, these are the number of tokens that it ends up selecting from based on the previous token, alongside the input tokens. It then randomly chooses one based on temperature settings.

It’s why if you turn these models’ temperature settings really high they output pure nonsense both conceptually and grammatically, because the tenuous thread linking the previous token’s context to the next token has been widened enough that it completely loses any semblance of cohesiveness.

Why would I save something for posterity when I could save it for posterior?

Saving this comment for posterior

https://github.com/hykilpikonna/hyfetch

I like hyfetch because it has the largest os compatibility.

It feels like the spiritual successor to neofetch tbh.

I’d say mostly energy savings and CPU usage efficiency

KDE separated out into Plasma and the utilities and apps separately at KDE 5. Previously it was all one package, so there is a bit of a confusing distinction.

Figured a link would help: https://gitlab.com/nonguix/nonguix

Ignore the weird wording about not promoting it on the page, it’s just a warning to keep people from complaining about the nonguix packages to the guix devs, but there’s lots of crossover

KDE is not, Plasma is:

https://guix.gnu.org/en/manual/devel/en/guix.html#Desktop-Services

I use guix cause having an entire OS centered around Scheme is cool and based.

Wearing out the parentheses keys on my keyboard

You wouldn’t necessarily punish the person that modified Linux either, you’d punish the person that uses it for a nefarious purpose.

Important distinction is the intention to deceive, not that the code/model was modified to be able to be used for nefarious purposes.

Ah, no not the template files for the individual containers, but the project descriptors are just compose files.

They’re 1-1 compose files.

The app just saves them as compose files and then runs docker compose in the backend.

it is EXTREMELY barebones