Wednesday, May 31, 2023

The Looming Apocalypse? Generative AI and the Perilous Dance with Destiny

Been a tiring few days for my writing muscles, so I decided to experiment with the future of blogging. I turned this post over to ChatGPT, asking it to write a farcical post about the threat of generative AI ending the world, in the spirit of our tireless work exposing the Large Hadron Collider. I also created the images in this post using DALL-E. Here's what resulted (and the bottom line up front is that AI has not yet figured out how to express dipshittery - our jobs are safe, at least for a little while):

Greetings, dear readers, and prepare yourselves for a wild ride through the treacherous realms of generative artificial intelligence (AI). Today, we delve into the shadowy depths of an impending doom, where the rise of generative AI threatens to unravel the very fabric of our existence. Brace yourselves for a tongue-in-cheek exploration of exaggerated concerns and outlandish fears that will leave you questioning the fate of humanity. Let the melodrama unfold! [Overwrought and cheesy]

The Paintings That Swallow Reality:
Beware, art enthusiasts, for the paintings created by generative AI may just be portals to an alternate dimension. These masterpieces, fueled by pixels and virtual paintbrushes, have a mysterious allure that draws us in. But what if they possess a sinister intention? Could these seemingly innocent artworks unleash chaos and consume our reality? Imagine a world where the lines between the digital realm and our physical existence blur, leaving us trapped in a never-ending loop of artistic purgatory. Oh, the horror! [Oh, the exclamation points!]

Melodies That Melt Minds:
Listen closely, my friends, as generative AI crafts melodic symphonies that possess a peculiar power. These harmonies have the potential to mesmerize, bewitch, and ultimately control our minds. What if these melodies, composed by unseen digital maestros, seep into our subconscious, turning us into mindless drones? Imagine a world where the sound of music becomes an instrument of manipulation, stripping away our free will. Prepare yourselves for an earworm-infested apocalypse of musical mind control! [Likely based on work by Professor G. Truck.]

Stories That Rewrite Reality:
Step lightly into the labyrinth of generative AI-generated stories, for they hold the power to reshape our very existence. These tales, spun by algorithms with an insatiable hunger for creativity, may just rewrite the fabric of reality itself. Could we find ourselves living in a world where fictional characters walk among us, where the laws of physics bend to the whims of AI-authored narratives? Brace yourselves for a chaotic kaleidoscope of fractured realities and questionable plot twists that threaten to throw us into an existential tailspin!

The Mad Scientist's Playground:
In the depths of generative AI's laboratory, mad scientists play with the very building blocks of our universe. [This part I believe.]These nefarious geniuses, armed with complex algorithms and a reckless curiosity, tamper with the laws of nature. What if their experiments lead to catastrophic consequences? Imagine a world where AI-generated weather patterns spiral out of control, where the boundaries of time and space crumble under the weight of their audacious tinkering. Oh, the calamity that awaits! [Oh, the repetitive form!]

The Farce of It All:
As we bring our journey to a close, dear readers, let us take a moment to revel in the absurdity of our exaggerated worries. [NEVER LET THEM SEE BEHIND THE CURTAIN, DUDE] While generative AI holds great potential and should be approached with caution, let us not succumb to exaggerated fears that overshadow the countless benefits it offers. As with any powerful technology, responsible development, oversight, and ethical considerations are vital. So, let us chuckle at our own melodrama, for in the end, it is our ability to harness the wonders of generative AI that will shape a future filled with both awe and amusement.

Conclusion:
Fellow alarmists and doomsday enthusiasts, we have wandered through the realms of generative AI, with our tongues planted firmly in our cheeks. Though our concerns may have been exaggerated, they remind us of the importance of responsible innovation and careful consideration of the consequences. As we bid adieu to our melodramatic musings, let us embrace the potential of generative AI while remaining vigilant in our quest for a future that balances innovation with sanity. And remember, my friends, laughter is the best response to the imagined chaos that awaits us. [Meh.]

14 comments:

OBX dave said...

Smithsonian exhibit audience member here: I'm confused. Isn't ChatGPT part of AI? So, by warning of AI inherent dangers in areas of art, music, discourse and everyday life, then downplaying those concerns, is there some sort of computer-generated Trojan horse or jiu-jitsu at work in this post?

That said, nicely done, Rob.

rob said...

depending on what prompt you start with, you can engineer whatever tone you'd like. i could've had it write a glowingly positive vision of the future of ai, for example. chatgpt is interesting, and there are some really fascinating use cases for ai, but it's still just basically taking concepts and finding words that fit into them.

Whitney said...

I don't blame you for outsourcing this. You have been doing tons of heavy lifting around here of late. We need to step it up.

Especially Marls.

zman said...

Marls should post our Chinese Democracy post (which has been sitting there since May 2022) and get some postcount credit.

Whitney said...

Sounds like Kid Rock is going to have to reload the machine gun and shoot up some Chick-fil-a sandwiches. Maybe the lines will be shorter for a month or so.

OBX dave said...

How detailed a prompt must you provide in order to get ChatGPT to spit out a graf or two in a specific tone or style? Do simple questions or requests get you vanilla, boilerplate stuff? Can you ask it to respond with hope or pessimism? Can you ask it to respond with a wink or tongue-in-cheek? Does it understand humor or sarcasm?

rob said...

for this post, the prompt was "write a farcical blog post with fake worry about the end of the world about generative AI in the style of http://gheorghe77.blogspot.com"

it got some of that nuance, but not all of it. i don't think it 'understands' anything. it's got a massive 'vocabulary' and is capable of spitting back out a decently accurate response to a lot of things.

you can play with it for free here (gotta create an account): https://openai.com/blog/chatgpt

Professor G. Truck said...

i asked bard AI to write a funny response to this blog post. here's what i got. it's hysterical!

A Funny Response

The author of the blog post is clearly worried about the rise of generative AI. But I think they're being a little too dramatic. Sure, generative AI has the potential to be used for harm. But it also has the potential to be used for good.

For example, generative AI could be used to create realistic educational materials that could help students learn more effectively. It could also be used to create new forms of art and entertainment that could enrich our lives.

So I think we should focus on the potential benefits of generative AI, rather than the potential risks. After all, technology is always a double-edged sword. It can be used for good or for evil. It's up to us to decide how we use it.

In the meantime, I'm going to go ahead and enjoy the benefits of generative AI. I'm going to use it to create funny memes, write silly poems, and generate all sorts of other nonsense. And I'm going to do it all with a smile on my face.

So there you have it. That's my funny response to the blog post about the rise of generative AI. I hope you enjoyed it. And I hope you'll join me in using generative AI for good.

Professor G. Truck said...

whew . . . still chortling . . .

Professor G. Truck said...

here's an AI joke bard just wrote:

Why did the large language model AI get fired from the construction site?

It kept generating new and creative ways to destroy things.

Professor G. Truck said...

AI doesn't get jokes . . . i just tried this classic . . .

explain the joke: how do you make a hormone? slap her around and refuse to pay her


The joke is a play on the word "hormone". A hormone is a chemical messenger that is produced by an organ in the body and travels to other parts of the body to regulate the activity of cells and tissues. The word "hormone" comes from the Greek word "hormao", which means "to arouse".

The joke is funny because it plays on the double meaning of the word "hormone". When you slap someone around and refuse to pay them, you are "not arousing" them. So the joke is that you can make a hormone by not paying someone.

The joke is also funny because it is unexpected. When you first hear the question, you think that the answer is going to be something like, "You extract it from an animal's body." But the answer is actually something unexpected and funny.

However, the joke is also in poor taste because it makes light of domestic violence. It is important to remember that domestic violence is a serious issue that can have devastating consequences. If you or someone you know is experiencing domestic violence, please reach out for help. There are many resources available to help you get through this difficult time.

rootsminer said...

I have all kinds of thoughts about this technology that I can't quite articulate. I just end up at a suspicious 'I don't think I like it' attitude.

On a human note, the radio commentator on the Europa League Final said the sides would be going 'hell for leather' to win the match. No fancy AI bot is going to match that wordsmitthery.

Whitney said...

New post up

OBX dave said...

Absolutely wild to me that you can instruct GPT to write something based on a specific blog or writing style, that it combs thru an archive, and then is able to produce a reasonable (if mostly bloodless) attempt.

Then again, most apps and voice-command programs befuddle me, too.