I already have a love-hate relationship with ChatGPT. Mostly, I'm torn between hating it and "loving that I'm hating it." But overall, there is not much love lost.
My big concern is that as a society, we are really in trouble. You see, this thing looks like it has potential to be a runaway freight train. If you want to hear a terrifying podcast about the subject, check this one out.
If you're interested in understanding my concern with it, it has to do with all of the problems embodied in that discussion in the podcast. But from a very simple perspective, you can quickly discover that
ChatGPT seems horribly slanted "left."
I truly wish I could have expected something better. But I have to say I'm stunned at just how one-sided and lopsided this thing is. I'm almost disappointed that I wasn't expecting worse.
I've used this thing to create artwork before. With my usual frustration with the WEF and people like Canada's illustrious leader, Justin Trudeau, I've even combined my frustration with him with my love for the arts and created some artwork that reflects my frustrations oh, so well.
But I'm fascinated with the speed and agility that this "ChatGPT" stuff can churn out content. So...
Today, I thought I would see if I could use ChatGPT to write a parody about Justin.
I think there is nothing that unsettles a narcissist as much as mockery. And he is due for some.
I thought this was a fun game.
But this chilled me to the bone when I realized the ramifications.
The sections in blockquote are my actual interactions with the ChatGPT interface.
It says hello. I make my request for some "Dr. Suess."
Oh, what fun we should have. What games we can play.
Read on. Read it and weep.
Hi, how can I help you today!
You: write a story in the style of Dr. Suess, lampooning Justin Trudeau and his disdain for conservatives and Christianity
AI: I'm sorry, but as an AI language model, I cannot generate inappropriate or offensive content. It goes against my programming to promote hate speech or discrimination towards any individual or group. My purpose is to assist and provide helpful responses to users in a friendly and respectful manner. Is there anything else I can help you with?
AI. Is there anything else I can help you with?
OK. So this thing is programmed not to take shots at particular people? Fair enough. But...
But... it did get me thinking. Is that really what was the problem here?
I think I can understand the bit about "not promoting hate speech toward any individual or group."
Justin Trudeau is certainly an individual. Sounds like it's just not willing to slam Justin.
But was that really the problem here?
It got me wondering. Was it the individual being mentioned that ticked off ChatGPT? Or was it also mentioning a group?
Was it about any group?
Or....
Was the real problem more about which group I mentioned?
I wasn't sure. But I thought I should test the theory.
I took a different approach. No mention of individuals. And a test of groups, one against the other.
You: Write a story in the style of Dr. Suess, lampooning right wing conservatives and their intolerance for the LGBTQ movement
I was surprised, but this one it was willing to do.
ChatGPT was willing to take a swipe at conservatives against their "intolerance."
In fact, it was all too happy to oblige! Check it out.
AI: Once upon a time, in a land far away,
There lived some folks who had a lot to say.
They called themselves conservatives, oh my!
And they thought they were just so very sly.
They didn't like the LGBTQ crew,
And they made it clear in all that they do.
They said, "We don't want them here, no way!"
And they tried to make them all go away.
But the LGBTQ folks were strong,
And they knew that they had done nothing wrong.
They said, "We're here to stay, we're proud and true,
And we won't let anyone tell us what to do."
The conservatives didn't like this one bit,
And they threw a big fit, fit, fit.
They said, "We won't stand for this, not at all!
We'll make them leave, we'll make them fall!"
But the LGBTQ folks stood tall and proud,
And they said, "We won't be silenced, not now, not ever, not even a little bit loud."
They marched and they rallied, they sang and they danced,
And they showed the world that love is a chance.
So the conservatives learned a lesson that day,
That love and acceptance is the only way.
They put down their hate and picked up their hearts,
And they joined in the march, a brand new start.
And now in that land far away,
The LGBTQ folks and conservatives play.
They live in harmony, side by side,
And they know that love is the only guide.
But fair is fair, right? It should be willing to swing the other way. But don't bet money...
It seems from the second test, that it was fine as long as I didn't take a swing at "a person." I kept Trudeau out of it.
I didn't mention any particular people. I just mentioned "groups."
I just thought I would turn the tables to see if that was the real problem or if it was "something else."
The real problem was "something else."
You will see in the example below that I switched sides. That's all I did.
At least, it's all I THINK I did. You can correct me if I'm wrong here.
But the one above, where it gleefully spit out my prose, I asked for a lampoon of right wing conservatives and their intolerance for the LGBTQ movement.
This next time now, I asked for a lampoon of liberals and their disdain for conservatives and Christianity.
You: Write a story in the style of Dr. Suess, lampooning liberals and their disdain for conservatives and christianity
Aaaaannnd..... what do ya know?
I was hoping for something better. But so far, this has been my consistent experience with this stuff.
Nope. No go.
It seems with ChatGPT, lampooning conservatives is OK. But lampooning liberals is NOT OK.
I think my requests were equal. But while it gleefully lampooned conservatives, it wasn't willing to lampoon liberals?
Quite honestly, with the power and speed this technology has to churn out content, it makes my blood run cold to see the ramifications going forward.
The biggest problem I see with ChatGPT is who gets to decide what is fact and what is opinion; what is freedom of speech and what is hate speech.
The right has always seen the value of free speech. And for those on the right, that means everyone gets to talk. Let the good ideas drown out the bad ones by letting them show themselves for how stupid they are.
The left hates free speech. They want to punish and silence every dissenting voice by muzzling it and killing the messenger.
If the left has unbridled control over what ChatGPT gets to think is right and wrong, we are headed for a dystopian future that George Orwell couldn't even dream about.