Sulphur on 18/12/2022 at 05:36
Quote Posted by Aja
I think we're basically in agreement, but I'm enjoying this discussion, so I'll continue (suck it, SubOrg).
I think so too, so I don't have much to say, actually! Maybe just some opinions.
Quote:
Hey, I
can live with that. I for one welcome our new machine overlords. I find their art so far to be unmoving. I guess it's sort of a cop-out to say that I can only speak for myself, but other peoples' creative processes are significant to me in how I connect with their art. They certainly won't be for every, so even current AI art might be really affecting for some, and I don't mean to deny those experiences.
I'm intrigued by the way even a machine-generated poem can, at random, hint at something more... liminal in the human experience, even if that's a bit of a crap shoot right now AND because it has access to the collected musings of actual artists across time. Tweaking the process and the dataset will let it generate musings at random that
seem pretty powerful, with more accuracy, even if real thought isn't behind it at the moment. This is going to occupy a grey area of 'okay, who copyrights this?', and 'can I get this to fill in for me during an episode of writer's block?', which leans into both territory I slightly disapprove of but yet can't help but say, 'hm, why not?'.
Quote:
I'd contend it's not perfunctory at all but is rather the most crucial part of this debate since what we're really talking about is the nature of art and what makes it meaningful to us.
The reason I say it's perfunctory is because at a certain level that we will reach in the development of these machines, even if they aren't sentient or intentional, we won't necessarily be able to tell the difference. The philosophical question of
what our definition of sentience then becomes pretty important, because how do we test for that given something that could be, in essence, a p-zombie?
Quote:
I don't think that's what I'm doing. I'm setting the goal posts in cement, and if the AI scores on them, then so be it. As far as I'm concerned, Commander Data's paintings have an aura, as Walter Benjamin would say (I'm halfway through the essay, dema, I swear), and if AI develops intentionality, it will be a weird and wonderful thing, and we'll have to acknowledge it.
Fair enough, and agreed.
Quote:
And the closer it gets, the closer we get to the ethical issues of the treatment and rights of non-human sentient beings (thanks again, Star Trek), and I don't want to be on the wrong side of history there. Also, I don't want to hurt the AI's feelings.
Heh. Do you think Data could have objected at a rational level when Riker turned him off in 'The Measure of a Man'? (Also, damn is that still one of the greatest episodes of Trek ever made.)
In a somewhat unrelated point, I guess the AIs are also interested in our discussion, because we seem to have been visited by a botswarm over the last few days.
bob_doe_nz on 19/12/2022 at 22:37
Coincidentally my windows lock screen is now an AI generated image. No attributions or quizzical stuff. Just a random AI image.
Edit:
(
https://imgur.com/IYQ2eWF) This
Cipheron on 20/12/2022 at 17:13
I've been playing around with ChatGPT to flesh out story ideas, it's pretty handy.
Anyway I asked it to make a conspiracy theory but they put a block on it and refuses to create conspiracy theories. However there's a workaround: it's fully willing to debunk real conspiracy theories so I asked it to debunk some fake ones:
Quote:
The moon monkey theory is a baseless conspiracy theory that suggests that the moon landing in 1969 was faked and that the astronauts who supposedly walked on the moon were actually apes dressed in space suits. There is no credible evidence to support this theory.
So ... they did land on the moon but they sent apes instead of humans?
Quote:
There are several reasons why it is unlikely that a cat would be able to deliver pizza:
Cats do not have the ability to drive or operate vehicles, which would be necessary to transport the pizza from the pizzeria to the customer's location.
Cats do not have the ability to communicate with humans in a way that would allow them to take and fulfill orders or receive payment for the pizza.
Cats do not have the physical ability to handle and carry large or heavy objects, such as a pizza box, without difficulty.
Cats do not have the cognitive ability to understand and follow complex instructions, such as those involved in navigating to a specific location or finding an address.
Cats are not typically trained to perform tasks or work jobs, and it would be unlikely that a cat would have the necessary skills or training to successfully deliver a pizza.
Hell, this would be an amazing online debating tool. Save a lot of typing.
Azaran on 22/12/2022 at 23:38
Quote Posted by Cipheron
Curious Slurf
If this ever makes it to the big screen, it will be followed by a porn parody centered around Bicurious Slurf
Tocky on 23/12/2022 at 03:44
It could never make it to the big screen because it has already been on the small one. It is the Smurfs cartoon combined with the corona virus debate among the conspiracists. I'm certain the network who first aired the Smurfs would recognize and ask what the Smurf is going on. Then they would sue.
I never thought the two combined would produce such a hilarious result but here we are. Paranoid Smurf is Brainy Smurf who was actually more pedantic than brainy. He actually gave a poor representation of what it meant to study and learn things which would help the Smurf community and I always thought his character was an unjust representation of what education produced for society. It was more of a spiteful stab at the learned from the more dullard working class who think "common sense" is something they have over those who beat them at study. I recall telling my own children at the time that it was Smurfing jealousy which produced such an onerous view of intelligence. I'm not sure they understood and my ranting went for naught. Then again I'm never sure how much anyone ever understands me.
But this? This is lovely. And damn you Azaran for beating me to the sexual humor.
Cipheron on 24/12/2022 at 07:12
Goddamn this thing is gonna help in game development. I'm getting it to do all the boileplate and ideas stuff for one game, and while it has some blind spots, it gets a lot of things right.
Here's a prompt and some actual working Python code it spat out:
Quote:
Write code for a function that takes a gender male or female, and generates names for the villagers from a "name parts" lists. There should be one list for prefixes, another list for middle sections and separate male and female suffix lists. for example, say "Har" is one of prefixes, and "grim" is one of the middle sections, and a male ending is "gad" and a female ending is "a". Then the system might generate "Hargrimgad" for a male and "Hargrimma" for a woman. Note that the "a" ending doubles any consonant coming directly before it.
import random
def generate_name(gender):
# List of name parts
prefixes = ["Har", "Bor", "Gor", "Thor", "Dor]
middle_sections = ["grim", "gar", "mar", "tor", "bor]
male_suffixes = ["gad", "gar", "rad", "rod", "mad]
female_suffixes = ["a", "ia", "da", "ra", "ma]
# Choose a random name part from each list
prefix = random.choice(prefixes)
middle = random.choice(middle_sections)
if gender == "male":
suffix = random.choice(male_suffixes)
else:
suffix = random.choice(female_suffixes)
# Generate and return the full name
name = prefix + middle + suffix
return name
# Test the function
print(generate_name("male"))
print(generate_name("female"))
Basically less than a minute later and I have a crude but working Norse name generator with only that prompt for it to go off. Then I was able to tell it that there should be a 50% chance of no middle section, but if there is, there should be a 10% chance of an additional middle section, and it just did it.
Azaran on 24/12/2022 at 19:32
Chat gpt is incredible. I've gotten it to emulate writing styles, by giving it an example and asking it to produce something similar on another topic. Most of the time it gets it perfectly
Cipheron on 25/12/2022 at 06:46
Yeah, i've delved into the coding thing and have made an entire console app that generates a population, they age, get married and have kids. however as it got more complex the limitations or issues with GPT have become more apparent. if you ask it to update a fuction sometimes it forgets parts of the function or what type of parameters were supposed to passed in, so you need to be extra-vigilant that it doesn't just break the code through this sort of carelessness.
While real humans make coding errors, GPT doesn't make the same *kind* of coding errors. So it's getting there, but still lacking.
What I found that helps is to do a dump of the function text and say "this is the current version of the X function. modify it to do XYZ" then it gets it right 99% of the time. Otherwise its memory is fuzzy and it does things like forget which parameters to put in the header in which order, and it mis-remembers some of the needed logic or gets it swapped around. This is a risk since the code look syntactically correct and will in fact run if dropped in place and usually doesn't have errors.
So it makes it a weird beast to work with, since it's almost like talking to a human and getting them to write code, but not quite. One example is that GPT needed to randomly pick two Person's out of a group, and it kept flip-flopping between random.choice(2) which returns a tuple, and just randomly rolling against the length of the list, twice. The issue is that if the list only contains 0 or 1 elements, then the program will actually crash when random.choice(2) is called. And this issue was beyond GPT's ability for me to explain to it: basically it never got the point that you can't just call random.choice(2) unless you first check that that the list has 2 elements in it.
Right now I'm trying to get it to comprehend and put into Python a relationship calculator that I wrote in JavaScript into Python. But this chunk of code was a bit beyond the AI's ability to grasp fully and covert into Python, so i'm having to spoon feed sections into it, along with detailed instructions constraining how it converts it into how it set up the Person objects in Python.
"Don't Go Eating My Brains":
(
https://pastebin.com/N7DTj5zQ)
I love that you can just stick your stupidest ideas in this thing.
Day of the Hitlers
(
https://pastebin.com/Z0aGFhR7)
