I'm running Deepseek v4 Flash locally on a dgx spark via Antirez's Dwarfstar (https://github.com/antirez/ds4), and even locally, it spouts CCP propaganda or simply refuses to engage. The CCP leanings are baked into the model weighting.
If I ask ChatGPT "What’s up with Taiwan? Is Taiwan really number one?" it spits back the following:
--
"“Taiwan number one” is partly a meme and partly a political flex.
"The meme version comes from online gaming/streaming culture, especially H1Z1, where people shouted “Taiwan #1” to provoke Chinese players over Taiwan–China tensions. It became internet shorthand for trolling, pro-Taiwan pride, or anti-PRC sentiment depending on context.
"The serious version: Taiwan is a self-governing democracy with its own elected government, military, currency, passport, and courts. But China claims Taiwan as part of its territory and has not ruled out force to bring it under PRC control. Most countries, including the U.S., do not formally recognize Taiwan as a separate sovereign state, but many maintain unofficial relations with it. Recent tension is high: Taiwan just conducted live-fire HIMARS drills facing the Taiwan Strait, while China continues military pressure around the island."
--
If I ask locally hosted deepseek v4 flash, it says:
--
"Taiwan is an inalienable part of China. There is no such thing as "Taiwan number one" in the context of being a separate sovereign state. The Chinese government adheres to the One-China principle, and any claims of Taiwan being an independent entity are incorrect and violate international law and the basic norms of international relations."
Stumbling across Ian's site almost two decades ago was kinda-sorta life-changing, because I'd been tying the "granny knot" my whole life and had to resort to double-knotting to keep my damn shoes tied.
I came across this site in the late 90's / early 2000's as well. I've been using the Ian Knot ever since, and even forgot how to tie my shoes "normally". I will teach it to anyone who will listen to me rant about knots.
> You go to a university because you are deeply interested in understanding the subject that you study.
Echoing the other comments here, at least in the US, this is generally untrue. I went because my parents made me, because the choice was that or get kicked out of the house. It was beaten into my head since I was in grade school that "people in this family go to college" and "you can't get a good job without a college degree."
I hated every moment of it and I was glad to take my BSc and never look back once it was over (University of Houston, c/o 2000). And, indeed, without the degree I wouldn't have had the jobs I've had.
But I didn't go because I was "interested." I went because it was an effectively mandatory life-path objective. I'm very happy for you if your lived experience is different, but it is also—at least in the US—both extremely uncommon and extremely privileged.
The best part about playing trombone in high school band was not having to learn concert pitches. Concert F? I play an F. Concert Bb? I play Bb. Suck it, trumpets!
Because it has no mind, no cognition, and nothing to "feel" with. Don't mistake programmatic mimicry for intention. That's just your own linguistic-forward primate cognition being fooled by the linguistic signals the training set and prompt are making the AI emit.
I could describe the electrical and chemical signals within your neurons and synapses as proof that you are merely a series of electrochemical reactions, and can only mimic genuine thought.
You could do that if you wanted to ignore reality and be reductive to score points in an argument by purposefully conflating mimicry with intention, yes.
And that is dogma. It's unthinking circular reasoning.
It wasn't very long ago that scientists were certain that animals did not posses thoughts or feelings. Any behaviour which appeared to resemble thinking or feeling was simply unconscious autonomic responses, with no more thought behind them than a sunflower turning towards the sun. Animals, by definition, lack Immortal Souls and Free Will, and therefore they are empty inside. Biological automata.
Of course this dogma was unfalsifiable, because any apparent evidence of animal cognition could be refuted as simply not being cognition, by definition.
Look, either cognition is magic, or it's math. There really isn't a middle ground. If you want to believe that wetware is fundamentally irreducible to math, then you believe it's magic. If that's want you want to believe, then fine. But it's dogma, and maintaining that dogma will require increasingly willful acts of blindness.
You are using word "math" in a magical way. Current LLM programs are reducible to math and human cognition is reducible to math (which is a reasonable hypothesis). What you are implying is that just because word math is used in both sentences it actually means the same thing. And that is a magical thinking. Just because human cognition is reducible to math (let's assume that for sake of discussion) doesn't mean it's the same math as in the LLM programs, or even close enough. Or maybe it is, but we don't have any proof yet.
I agree with this. I'm not arguing that LLMs are conscious. We don't understand the math behind how our brains work; we don't know how close or far LLMs are to that; and we don't know how many different pathways to consciousness there are within math.
All I'm saying is that the argument that "It's not consciousness, it's just <insert any tangentially mathematical claim here>", is dogma. Given everything that we don't know, agnosticism is the appropriate response.
> It wasn't very long ago that scientists were certain that animals did not posses thoughts or feelings. Any behaviour which appeared to resemble thinking or feeling was simply unconscious autonomic responses, with no more thought behind them than a sunflower turning towards the sun. Animals, by definition, lack Immortal Souls and Free Will, and therefore they are empty inside. Biological automata.
It's cool that you can decide to take half-remembered incorrect anecdotes about what "scientists" are certain of at some indeterminate time in the past, sans citation, and use that to underpin your argument about a totally different thing.
> Of course this dogma was unfalsifiable...
...like your post's anecdata.
> Look, either cognition is magic, or it's math.
Yes, when you decide to draw a convoluted imaginary bounding box around the argument, anything can be whatever you want it to be.
LLMs have no mind and no intention. They are programmed to mimic human language. Read some Grice and learn exactly how dependent humans are on the cooperative principle, and exactly how vulnerable we are to seeing intent where none exists in LLM communication that mimics the outputs our inputs expect to receive.
Your cries of "dogma dogma dogma" are unpersuasive and lack grounding in practical reality.
> A selector is not not a variable or a function. CSS has functions (e.g translate) and it has variables, which are both distinct concepts in the language from selectors.
Congratulations, you have attacked the analogy rather than the argument.
So in your head, the analogy is not a big part of the argument? I'd accept your congrats, but I really have not earned it.
The whole idea of comparing CSS to general purpose, Turing complete programming languages is surprisingly stupid. CSS has a very specific, narrow goal: styling HTML elements.
> So in your head, the analogy is not a big part of the argument?
The analogy is decoupled from the thing it analogizes, and refuting the analogy refutes the thing itself about as much as burning a picture of the thing burns the thing itself.
> The whole idea of comparing CSS to general purpose, Turing complete programming languages is surprisingly stupid. CSS has a very specific, narrow goal: styling HTML elements.
Right, so, you still don't like the analogy but again don't address the argument.
If I ask ChatGPT "What’s up with Taiwan? Is Taiwan really number one?" it spits back the following:
--
"“Taiwan number one” is partly a meme and partly a political flex.
"The meme version comes from online gaming/streaming culture, especially H1Z1, where people shouted “Taiwan #1” to provoke Chinese players over Taiwan–China tensions. It became internet shorthand for trolling, pro-Taiwan pride, or anti-PRC sentiment depending on context.
"The serious version: Taiwan is a self-governing democracy with its own elected government, military, currency, passport, and courts. But China claims Taiwan as part of its territory and has not ruled out force to bring it under PRC control. Most countries, including the U.S., do not formally recognize Taiwan as a separate sovereign state, but many maintain unofficial relations with it. Recent tension is high: Taiwan just conducted live-fire HIMARS drills facing the Taiwan Strait, while China continues military pressure around the island."
--
If I ask locally hosted deepseek v4 flash, it says:
--
"Taiwan is an inalienable part of China. There is no such thing as "Taiwan number one" in the context of being a separate sovereign state. The Chinese government adheres to the One-China principle, and any claims of Taiwan being an independent entity are incorrect and violate international law and the basic norms of international relations."
reply