>How do they talk about themselves?
"You are a Large Language Model" in (system?) prompt would do the trick..
646 karma · joined October 16, 2025
"You are a Large Language Model" in (system?) prompt would do the trick..
Today, computers don't even have parallal/serial ports. Everyone has to pay the USB gods their tribute to have the mercy of allowing to program arbitrary IO from their computers....And they still need some kind of serial receptacle on the other end...
If I remember correctly, there were even sample programs included in this documentation.
QBasic's bultin help/documentation was good enough for me..
But it seems that he is falling for the LLM hype the same way. We all have the kid version of ourselves hiding somewhere within our grown versions, it seems...
Why did you think that? Did you see people use it like that? anything? really?
For me, computers became intriguing after I started programming in BASIC. Not before that. Before that I was just curious about what the big deal about these things are...
In the literature, there would be passages that describe how computer followed "instructions", but I never could make sense of that or understood what an "instruction" was. So it didn't really sway me either way. I just tried hard and remained curious to understand what this "instruction" was and how I could give it to computers...
May be your falling the same way for LLMs now..
Seriously, how do you brainstorm with an entity that would 180 if pushed a bit..How can you take anything it say at face value?
Now you have what you think is the ideal architecture. Since you didn't implement it, you didn't discover it was not the ideal one mid way into the implementation.
May be it is too complicated, but you wouldn't know, because LLM is doing the implementation. If you did implement it yourself, you might have spotted a critical point that might simplify the whole thing...
Tell me again how Consciousness is an illusion..
Ours. Or every ones..We can easily accept that we inhabit the same spacetime. Why is it hard to imagine the same for consciousness?
space is an illusion...The only thing that is absolute is consciousness, on top of which all illusions stand.
What is a `ctx` and why do I need that? These are all hacks. Graphics programming in bolted on HTML in the form of canvas. It is a horrible platform for doing fun graphics programming when compared to qbasic.
>For delays, you define "sleep" (one line) and write "await sleep(500)" inside a loop, just like with "SLEEP" in QBASIC.
Kindly provide the code for this sleep function and tell me how a beginner who is trying draw some graphics on screen is supposed to figure that.
Exactly. AI generates imitations of the past. So does a paint brush at its fundamental.
Think of what individuality can do with AI assistance. AI is like guns. It levels the playing field. Now it does not matter how much your marketing budget is. If you can use AI in a smart way that does not dilute your essence, then you got a better chance to shine, than before..hopefully...
s/made/revealed/
Oh yea? give me the equalent of PLAY function. Or the PSET function to turn individual pixels on and off on the screen. Give me the function to read the color of any onscreen pixel (admittantly not QBASIC but some C variant)...
FFS you can't even draw something delayed on screen without having to deal with the setTimeout, setInterval madness. That alone would kill any interest that a kid might be starting out with!
They are not dumb. Just not initiated in the direction required to understand this. And the purpose of incessant marketing is to prevent them from doing so..
No, they are not. There write programs like they write prose. There is 100% adherence to grammar and spelling when they write prose, but yet what they write is unintelligible and needlessly verbose.
When they write computer programs there is 100% adherence to good practices, but eventually the program becomes so unintelligible and verbose that only an LLM can make any sense of it going forward. But even then, changes result in more things breaking than they fix. But the number of bugs slashed goes through the roof. Management is happy!
>Of course you can misuse it.
I think the proper way to use it is to use it as a better search tool. But I don't think AI marketing and valuation is going to be sated by such a use case.
The problem is not that it is super smart. It is that it is super dumb and super powerful. Like a boulder falling down.
Humanity is like this bunch of utter morons who has rolled a big boulder up a big mountain and let it loose at the top, and standing at the bottom is clapping and cheering seeing it coming down, guided by random collisions in its path, and with real probability that it will land on them....
If I know how LLM work, and what it is trained on, I don't have to "explore" it to understand what it can do for me. The only variable is how deeply one knows how "LLMs" work, and that makes up all the on going arguments by lay people...
The boulder, it even found a path down the mountain. on its own, by doing so-amazing path finding its own super amazing path finding algorithm, and all the boulders co-ordinated falling down, ON THEIR OWN! And they all reached the ground!
I tell you! The future may be these boulders washing your underpants and putting you to sleep. It is clear!