I’m jelly, my setup is just old PCs at this point and my wife is not keen on letting me expand the storage lol

I still use it for server context, newer apts then Debian usually and no snap stuff I’ve come across (mostly use docker anyway)

Oh boy, well yikes nvm lol

Yeah, rumble seems like the only viable alternative and they got lambasted for hosting so much right wing conspiracy nuts when it first launched lol

If you use yt music and watch YouTube as your main entertainment, it’s well worth it imo.

With that said, I’ve been degoogling and this is probably the one I won’t be able to break.

I work in the financial industry and we were talking about it in our “huddle” yesterday.

It ain’t just Lemmy

I mean I literally can test it immediately lol, a nodered js function isn’t going to be dangerous lol

Or an AHK script that displays a keystroke on screen, or cleaning up a docker command into docker compose, simple shit lol

Just one thing, trumps populist rhetoric is what won him some Bernie supporters, the idiots but still.

I don’t see how that’s different honestly, then again I’m not usually asking for absolute truth from LLMs, moreso explaining concepts that I can’t fully grasp by restating things in another way or small coding stuff that I can check essentially immediately if it works or not lol.

Took that a slightly different way then I was expecting, my point is we have to be on the lookout for bullshit when getting info from other people so it’s really no different when getting info from an LLM.

However you took it to the LLM can’t determine between what’s true and false, which is obviously true but an interesting point to make nonetheless

Bruh so much of our lives is made up of people lying, either intentionally or unintentionally via spreading misinformation.

I remember being in 5th grade and my science teacher in a public school was teaching the “theory” of evolution but then she mentioned there are “other theories like intelligent design”

She wasn’t doing it to be malicious, just a brainwashed idiot.

It absolutely got worse around 5 or so years ago, literally filled with suggestions instead of the fucking search term.

Sure capitalism is going to capitalize and make false claims, but the extreme over reaction to the contrary (much like with crypto) is likely to lead (much like with crypto) to normal people shunning it while only the already rich and powerful really benefit.

It actually absolutely will because of the blind antiAI sentiment

Small bits of code, language related tasks, basic context understanding, not metrics I have literally measured simply noticed has improved compared to non reasoning models in my homelab testing. 🤷‍♂️

Lul yes but no, but they are clearly better at many types of tasks.

I see you don’t know how crypto works lol

Advanced Reasoning models came out like 4 months ago lol

Also mod support is hit or miss

I use oobabooga, little bit more options in the gguf space then ollama but not as easy to use imo. Does support openAI api connection though so can plug in other services to use it.