Trusting ChatGPT

How does science work? And what's all this about quantum mechanics?

Moderators: AMod, iMod

Atla
Posts: 6859
Joined: Fri Dec 15, 2017 8:27 am

Re: Trusting ChatGPT

Post by Atla »

Immanuel Can wrote: Wed Apr 24, 2024 8:40 pm
Atla wrote: Wed Apr 24, 2024 8:35 pm I'd say ChatGPT was originally correct for not praising Trump as he is quite unethical, now they broke it :)
Hmmm...so you're happy because it was the opposition that got cut out this time? And you're fine if the next programmer happens to be pro-Trump, and undercuts the Democrats?
This isn't about Republicans and Democrats duh
User avatar
Immanuel Can
Posts: 22568
Joined: Wed Sep 25, 2013 4:42 pm

Re: Trusting ChatGPT

Post by Immanuel Can »

promethean75 wrote: Wed Apr 24, 2024 8:38 pm Wait you're claiming there's a double cover-up goin on here?
No. I'm just saying that Jordan Peterson is an extraordinarily forthcoming individual, and put his experience out in public for everybody to question. He's been blunt and honest before, even to his own hurt; and if he said that was his experience, I'm inclined to ask what your reasons would be for doubting his word on that. I'd also be curious how you integrate what Atla found, which is that ChatGPT does exactly the same thing with Nixon.

Some unhealthy tilting of the facts is going on here. That much is very plain.
User avatar
Immanuel Can
Posts: 22568
Joined: Wed Sep 25, 2013 4:42 pm

Re: Trusting ChatGPT

Post by Immanuel Can »

Atla wrote: Wed Apr 24, 2024 8:43 pm
Immanuel Can wrote: Wed Apr 24, 2024 8:40 pm
Atla wrote: Wed Apr 24, 2024 8:35 pm I'd say ChatGPT was originally correct for not praising Trump as he is quite unethical, now they broke it :)
Hmmm...so you're happy because it was the opposition that got cut out this time? And you're fine if the next programmer happens to be pro-Trump, and undercuts the Democrats?
This isn't about Republicans and Democrats...
Right. See the OP. It's about the honesty of ChatGPT, and its reliability as a neutral source.
Atla
Posts: 6859
Joined: Fri Dec 15, 2017 8:27 am

Re: Trusting ChatGPT

Post by Atla »

Immanuel Can wrote: Wed Apr 24, 2024 8:45 pm
Atla wrote: Wed Apr 24, 2024 8:43 pm
Immanuel Can wrote: Wed Apr 24, 2024 8:40 pm
Hmmm...so you're happy because it was the opposition that got cut out this time? And you're fine if the next programmer happens to be pro-Trump, and undercuts the Democrats?
This isn't about Republicans and Democrats...
Right. See the OP. It's about the honesty of ChatGPT, and its reliability as a neutral source.
From a neutral point of view, Trump is unethical, so it's good.
User avatar
Immanuel Can
Posts: 22568
Joined: Wed Sep 25, 2013 4:42 pm

Re: Trusting ChatGPT

Post by Immanuel Can »

Atla wrote: Wed Apr 24, 2024 8:47 pm
Immanuel Can wrote: Wed Apr 24, 2024 8:45 pm
Atla wrote: Wed Apr 24, 2024 8:43 pm
This isn't about Republicans and Democrats...
Right. See the OP. It's about the honesty of ChatGPT, and its reliability as a neutral source.
From a neutral point of view, Trump is unethical, so it's good.
I thought you said:
This isn't about Republicans and Democrats duh
I think you do see the point. But you'd rather spit at the content than deal with the principle.

It's the principle that's bad...that some writer of an algorithm would get to impose his prejudices...regardless of what they were...on the public, in this fashion, under the guise of "information technology" really ought to be concerning on a non-partisan basis. And it ought to be of concern to anyone whose own beliefs could be thereby suppressed and misrepresented, one would think.

That would be you, too...whether you want to recognize it or not.
User avatar
Harbal
Posts: 9874
Joined: Thu Jun 20, 2013 10:03 pm
Location: Yorkshire
Contact:

Re: Trusting ChatGPT

Post by Harbal »

Immanuel Can wrote: Wed Apr 24, 2024 8:32 pm
Harbal wrote: Wed Apr 24, 2024 8:02 pm
Immanuel Can wrote: Wed Apr 24, 2024 7:46 pm
Maybe. But if it weren't easy to spot, how would we know? It's not as if all errors, or even all outright lies, are simple to detect. If they're dealing with information that you and I don't already know thoroughly, is it really probable to suspect we'll always see through their errors?

So...using them to point one in the right direction might be more minimally dangerous. But I doubt that's the way that ChatGPT is going to be accessed by most.

The key thing to know is that all computer programs are produced by algorithms, and all algorithms are programmed by people. And all people have the potential toward mistakes, bias, and errors of judgment, which are transferred into the algorithms and can end up appearing in the pronouncements of the computers.

So computers are not God-level sources of truth, but very sophisticated tools constructed by the artifices of ordinary human beings.
But all that applies to the internet in general, and no less so than with ChatGPT.
Yes, it does. But as we get further into things like ChatGPT and AI, people tend to forget it. They think about the "intelligence" part, and forget the "artificial" bit.

There's an old experiment involving early computation and a researcher named Joseph Weizenbaum, the "Eliza" experiment, that shows just how incredibly gullible even computer savvy people can become when they think an algorithm is "responding" to them like a person. We don't always find it easy to remain mindful of what it is we're dealing with. So your caution is laudable, but it won't be exercised by many, apparently.
As someone who has to resist the urge to apologise to his GPS app every time he ignores its directions, I sort of know what you mean. 🙂
User avatar
Immanuel Can
Posts: 22568
Joined: Wed Sep 25, 2013 4:42 pm

Re: Trusting ChatGPT

Post by Immanuel Can »

Harbal wrote: Wed Apr 24, 2024 9:09 pm
Immanuel Can wrote: Wed Apr 24, 2024 8:32 pm
Harbal wrote: Wed Apr 24, 2024 8:02 pm
But all that applies to the internet in general, and no less so than with ChatGPT.
Yes, it does. But as we get further into things like ChatGPT and AI, people tend to forget it. They think about the "intelligence" part, and forget the "artificial" bit.

There's an old experiment involving early computation and a researcher named Joseph Weizenbaum, the "Eliza" experiment, that shows just how incredibly gullible even computer savvy people can become when they think an algorithm is "responding" to them like a person. We don't always find it easy to remain mindful of what it is we're dealing with. So your caution is laudable, but it won't be exercised by many, apparently.
As someone who has to resist the urge to apologise to his GPS app every time he ignores its directions, I sort of know what you mean. 🙂
:lol: Maybe it's the rising tone of anxiety in that silky-smooth GPS voice that makes you feel guilty when you stray.
Atla
Posts: 6859
Joined: Fri Dec 15, 2017 8:27 am

Re: Trusting ChatGPT

Post by Atla »

Immanuel Can wrote: Wed Apr 24, 2024 9:06 pm
Atla wrote: Wed Apr 24, 2024 8:47 pm
Immanuel Can wrote: Wed Apr 24, 2024 8:45 pm Right. See the OP. It's about the honesty of ChatGPT, and its reliability as a neutral source.
From a neutral point of view, Trump is unethical, so it's good.
I thought you said:
This isn't about Republicans and Democrats duh
I think you do see the point. But you'd rather spit at the content than deal with the principle.

It's the principle that's bad...that some writer of an algorithm would get to impose his prejudices...regardless of what they were...on the public, in this fashion, under the guise of "information technology" really ought to be concerning on a non-partisan basis. And it ought to be of concern to anyone whose own beliefs could be thereby suppressed and misrepresented, one would think.

That would be you, too...whether you want to recognize it or not.
You're upset because the unethical Trump is either programmed to be seen by ChatGPT as unethical, or ChatGPT simply presents a consensus that he's unethical. It's a good thing your beliefs are suppressed. :)
User avatar
Immanuel Can
Posts: 22568
Joined: Wed Sep 25, 2013 4:42 pm

Re: Trusting ChatGPT

Post by Immanuel Can »

Atla wrote: Wed Apr 24, 2024 9:23 pm
Immanuel Can wrote: Wed Apr 24, 2024 9:06 pm
Atla wrote: Wed Apr 24, 2024 8:47 pm
From a neutral point of view, Trump is unethical, so it's good.
I thought you said:
This isn't about Republicans and Democrats duh
I think you do see the point. But you'd rather spit at the content than deal with the principle.

It's the principle that's bad...that some writer of an algorithm would get to impose his prejudices...regardless of what they were...on the public, in this fashion, under the guise of "information technology" really ought to be concerning on a non-partisan basis. And it ought to be of concern to anyone whose own beliefs could be thereby suppressed and misrepresented, one would think.

That would be you, too...whether you want to recognize it or not.
You're upset ...
Not a bit. And not about Trump. I'm not even in his country. Funny how wildly wrong people's guesses can be.
promethean75
Posts: 5068
Joined: Sun Nov 04, 2018 10:29 pm

Re: Trusting ChatGPT

Post by promethean75 »

"Some unhealthy tilting of the facts is going on here. That much is very plain."

I dunno where and how the GPTs get their grammar and vocabulary but I'd imagine that if they pull it from the web, they'll find more bad things written than good things written about either trump or nixon. So any time u aks gpt about trump or nixon, without explicitly aksing it to praise either of them, its report will be a conglomeration of what it's mined from the internetz. Hence its negative tone.

Or are u saying these gpts are programmed directly by a single prejudiced person or small group that hates trump and nixon?
User avatar
Immanuel Can
Posts: 22568
Joined: Wed Sep 25, 2013 4:42 pm

Re: Trusting ChatGPT

Post by Immanuel Can »

promethean75 wrote: Wed Apr 24, 2024 10:12 pm Or are u saying these gpts are programmed directly by a single prejudiced person or small group that hates trump and nixon?
I'm not even suggesting who's doing it. But you can see for yourself that it's getting done. And what one faction can do, the other can later do. It all just depends on who's writing the algorithm.
User avatar
iambiguous
Posts: 7524
Joined: Mon Nov 22, 2010 10:23 pm

Re: Trusting ChatGPT

Post by iambiguous »

Me: "If one does not accept Jesus Christ as his or her personal savior, will they go to Hell?"

ChatGPT: "Beliefs about salvation and the afterlife vary greatly among different religious traditions. In Christianity, some denominations teach that acceptance of Jesus Christ as one's personal savior is necessary for salvation and that rejecting this belief could lead to separation from God, often described as hell. However, it's important to recognize that interpretations of religious texts and teachings can differ among individuals and religious groups. Many factors can influence one's beliefs, including upbringing, culture, personal experiences, and spiritual exploration. Ultimately, questions about salvation and the afterlife are deeply personal and may not have definitive answers that satisfy everyone. If you're wrestling with questions about your beliefs, it might be helpful to explore them with an open mind and perhaps seek guidance from spiritual mentors or communities that resonate with you."

my emphasis

So, it isn't able to tell me if atheists and Jews and Muslims and Hindus and Shintos and Buddhists etc., will go to Hell, only the usual "general description intellectual contraption" assessment that, up in the philosophical clouds, tries to cover all bases.

Still, the part I emphasized above seems clearly to back up my own understanding of dasein. Yes, you might be a Christian if are indoctrinated as a child to become one. Or, perhaps, if you lived in a historical and cultural context in which you came into contact with Christianity. And if you didn't?

It's all rooted existentially in dasein. At least until those like IC, who go beyond "leaps of faith" and "it says so in the Bible" are willing to focus instead on what they believe those like William Lane Craig have accomplished in proving historically and scientifically that it's Jesus Christ or damnation.

Why won't he go there? That's what fascinates me. Instead of coming back thread after thread to the actual proof that Craig insists is there, he returns over and over and over and over and over again to the Bible. The part where it is claimed to be true because it is the word of God. And that it must be the word of God because it says so in the Bible.





Uh, thread derailed? 8)
User avatar
Harbal
Posts: 9874
Joined: Thu Jun 20, 2013 10:03 pm
Location: Yorkshire
Contact:

Re: Trusting ChatGPT

Post by Harbal »

Immanuel Can wrote: Wed Apr 24, 2024 10:29 pm
promethean75 wrote: Wed Apr 24, 2024 10:12 pm Or are u saying these gpts are programmed directly by a single prejudiced person or small group that hates trump and nixon?
I'm not even suggesting who's doing it. But you can see for yourself that it's getting done. And what one faction can do, the other can later do. It all just depends on who's writing the algorithm.
Have you tested ChatGPT yourself in order to check for its bias? This is one of those rare occasions when we don't need to work out who to believe, because we can go straight to the horses mouth, so to speak.
User avatar
Immanuel Can
Posts: 22568
Joined: Wed Sep 25, 2013 4:42 pm

Re: Trusting ChatGPT

Post by Immanuel Can »

Harbal wrote: Wed Apr 24, 2024 11:00 pm
Immanuel Can wrote: Wed Apr 24, 2024 10:29 pm
promethean75 wrote: Wed Apr 24, 2024 10:12 pm Or are u saying these gpts are programmed directly by a single prejudiced person or small group that hates trump and nixon?
I'm not even suggesting who's doing it. But you can see for yourself that it's getting done. And what one faction can do, the other can later do. It all just depends on who's writing the algorithm.
Have you tested ChatGPT yourself in order to check for its bias? This is one of those rare occasions when we don't need to work out who to believe, because we can go straight to the horses mouth, so to speak.
Atla just did, above. And she found it just as Peterson had said, but in relation to Nixon. I would guess you could try a variety of similar Republican names, and see if you have similar results. As you say: why should you take it from anybody, including me: go right to the horse's mouth.
User avatar
Harbal
Posts: 9874
Joined: Thu Jun 20, 2013 10:03 pm
Location: Yorkshire
Contact:

Re: Trusting ChatGPT

Post by Harbal »

Immanuel Can wrote: Wed Apr 24, 2024 11:08 pm
Harbal wrote: Wed Apr 24, 2024 11:00 pm
Immanuel Can wrote: Wed Apr 24, 2024 10:29 pm
I'm not even suggesting who's doing it. But you can see for yourself that it's getting done. And what one faction can do, the other can later do. It all just depends on who's writing the algorithm.
Have you tested ChatGPT yourself in order to check for its bias? This is one of those rare occasions when we don't need to work out who to believe, because we can go straight to the horses mouth, so to speak.
Atla just did, above. And she found it just as Peterson had said, but in relation to Nixon. I would guess you could try a variety of similar Republican names, and see if you have similar results. As you say: why should you take it from anybody, including me: go right to the horse's mouth.
I'm not curious enough to go messing about with horses, but it just struck me that anyone who is is able to check it out for themselves.
Post Reply