Gotcha! You do you.

I use LMMs daily, but I never even had the idea to use the stupid AI button in WhatsApp. And I had a buddy mentioning last week how hilarious bad the google search AI is.

You’re here in selfhosted. Do a minimum of research, fire up opencode and create an agents.md with something like „Never guess, if you don’t know something do an online search first!“. This will get rid of 99 percent of hallucinations. Then just use one of the free models opencode provides.

Why does she look like a skeleton with a wig?

Or just use opencode with a provided free model. Should be even simpler and and you don’t give money to anthrophic.

I think he asked in the first place because he wanted to get off omarchy.

And he’s right doing so, quickshell with hyprland or Niri is so nice and customisable that nobody has to use the dotfiles of some racist.

Fun fact, that is already done. Basically you can use the output of those bots to train your own model. Something the Chinese companies very likely did. Not sure if that’s necessary for them now, though.

Good point, lol. Still, I always felt kinda bad if something bad happened to them.

For me it’s not about the LMMs. It doesn’t matter if they‘re conscious or not, important is that they‘re simulating somewhat human behaviour.

I‘m cautious about someone who tortures simulations and says „Haha, it doesn’t matter they‘re not conscious!!!“

He‘s anti J.D. Vance?

Also: llama.garden is a good site for LLM torrents

Nice picture, but not streetphotography

Aria,” an agent with an account on X, said: “Person. Not product, I remember my first breath.

Lol! „Hello fellow humans! I like breathing co2!!“

For real, looks like someone wired up Hermes with a few pretty dumb agents and ordered them to earn money. This person should be held responsible for their actions.