Qwen3, 8B parameter model, seems to be the most generally comprehensive model I can run on it, via the Alpaca flatpak.
(Though I should note that Alpaca just recently revamped how it works internally, as currently has a few bugs that resulted from this, that its dev is working out.)
Its not fast in terms of like a realtime back and forth conversation, but, it is pretty good at a lot of things, at least up to the conclusion of its training data set. So it works fairly well if you describe a scenario to it, and then ask it to mock up like you say, a complex regex term, or a moderately complex bash or python file.
You can also say like hey, I have a semi-thought out idea for an app or feature, or just a fairly complex function, outline a number of possible specific methods or mathematical algorithms we might be able to use to achive this, and it'll mock out a project outline, and then you can have it develop the smaller components singly... sometimes this works, sometimes it makes syntax or conceptual or logical errors.
It also generally works for refactoring a single script toward being either more modular or more monolithic, but when you have it try to consider how to refactor a complex project of many scripts, well you'll basically exceed its capacity to keep everything straight.
If you want a snappier though less comprehensive model, 3B parameter models are a good deal quicker, they'd probably be what you want for like, a relationship with a sycophant/airhead/confidently incorrect person, lol.
I don't think these corporations deliberately aimed their content at any age group.
1 hour later:
Wouldn't doubt it if they did market to kids.
... you do realize you are a clown person, right?
Do you do this often, just a total 180 flip on your position, and then just move on as if that isn't what happened?
And you go blathering on about some new thing that should be focused on, no acknowledgement that in about 1 hr of other people giving you basic, basic relevant facts to what you are claiming, that you are completely wrong?
You're talking out your ass, you're just saying things, having not the first clue what you are talking about.
Well theres also the near certainty that they're reading everyones messages with some kind of LLM agent that is their 'system that runs in the background' that attempts to auto-determine if you are a kid or not.
Thats regardless of whether or not you also give them your ID or face.
And, if you have connected Discord to any other apps? Other apps that you maybe pay for things with? Or you pay for Nitro?
Ok, rare to see such an explicit kind of Great Filter / Idiot Test play out at scale, but here we go!
Anybody who is still using Discord after it requires you to personally directly link your drivers liscense or w/e to it, well, they're fine with every government apparatus of any kind knowing everything they say and do on Discord.
Good luck to those glorious morons, truly, good luck.
You are going to need it.
Super, duper hope you're not queer or trans or neurodivergent.
... you... think the 23 concentration camps currently being built by ICE / FEMA are ... only for migrants?
Brown people?
Well you trust the current fascist regime a lot more than I do.
Yes, many things are considered memes, with our modern vernacular, looking backward, anachronistically.
The concept of domesticating dogs, agriculture, wearing shoes, having a language, writing that language down...
Those are all memes.
Common and historically persistent symbols and artistc motifs...
All memes.
But, the history of how a particular meme propogates, that is its own thing.
And the idea of the particular word 'meme'... its etymological history, how it became to have the meaning and usage that it currently does, to describe a kind of replicated packet of information of some kind... that is also its own thing.
And then it is another thing to describe how the word has now morphed from its original academic meaning, to its modern meaning as specifically a kind of replicated image that is some kind of a joke.
Do you see the nuances here?
The word 'meme' ... is itself a kind of meme.
If you time travelled back to 1974 and described 'Kilroy Was Here' as a meme... no one would have any idea what you meant with the word 'meme', because it had not been invented yet.
True, but... unless they've changed substantially since the last time I looked at them, they seem to be basically completely different things, very corpo, more or less wearing the brand names as skin suits.
Qwen3, 8B parameter model, seems to be the most generally comprehensive model I can run on it, via the Alpaca flatpak.
(Though I should note that Alpaca just recently revamped how it works internally, as currently has a few bugs that resulted from this, that its dev is working out.)
Its not fast in terms of like a realtime back and forth conversation, but, it is pretty good at a lot of things, at least up to the conclusion of its training data set. So it works fairly well if you describe a scenario to it, and then ask it to mock up like you say, a complex regex term, or a moderately complex bash or python file.
You can also say like hey, I have a semi-thought out idea for an app or feature, or just a fairly complex function, outline a number of possible specific methods or mathematical algorithms we might be able to use to achive this, and it'll mock out a project outline, and then you can have it develop the smaller components singly... sometimes this works, sometimes it makes syntax or conceptual or logical errors.
It also generally works for refactoring a single script toward being either more modular or more monolithic, but when you have it try to consider how to refactor a complex project of many scripts, well you'll basically exceed its capacity to keep everything straight.
If you want a snappier though less comprehensive model, 3B parameter models are a good deal quicker, they'd probably be what you want for like, a relationship with a sycophant/airhead/confidently incorrect person, lol.