Welcome to Bookchat! Where you can talk about anything; books, plays, essays, and audio books. You don’t have to be reading a book to come in, sit down, and chat with us.
Me: ChatGPT, write a short paragraph about the controversy over books written by artificial intelligence
ChatGPT: The emergence of books written by artificial intelligence has sparked a notable controversy within literary and creative circles. Advocates highlight the potential for AI-generated literature to push the boundaries of creativity and produce innovative, unexpected narratives. They argue that these AI-generated books could serve as a new form of art and expression, challenging traditional notions of authorship. However, critics express concerns about the authenticity and originality of AI-authored works, questioning whether they can truly capture the depth of human emotion and experience. The debate also delves into questions surrounding copyright, intellectual property, and the implications for the future of human creativity. As AI continues to evolve, the controversy over AI-written books underscores the evolving relationship between technology, creativity, and the essence of storytelling.
Me: I don't think AI can be truly creative
ChatGPT: Your perspective on AI's creativity is a common one and has sparked much debate. Some argue that AI's output is limited to patterns and data it has learned from existing sources, leading to a lack of true originality and creativity. Others, however, contend that AI systems, particularly those built on advanced neural networks, can generate novel and unexpected ideas by combining existing concepts in unique ways. While AI's creative process may differ from human creativity, it has shown the ability to produce artworks, music, and literature that some find genuinely innovative. The ongoing discussion about the nature of AI creativity is likely to continue as the technology advances and its capabilities become more refined.
Artificial intelligence, or AI for short, is inescapable these days. A steady stream of news stories flows out to us, so ubiquitous that one can’t help but wonder if they are not being generated by some AI troll farm to habituate us to its presence and lull us into acceptance. Like the proverbial frog in a pot of slowly heating water, we are afloat in a world of slowly increasing artificially created words and images.
In recent days, I’ve seen an article about white-collar workers facing displacement from AI bots, a reversal of the usual displacement of blue-collar workers by technological advances. AI-generated art is spreading through all sorts of creative work: “image generators like DALL-E 2, Midjourney and Stable Diffusion have made it possible for anyone to create unique, hyper-realistic images just by typing a few words into a text box.” Indeed, the encroachment of AI into the arts is one of the main issues in the strike by Hollywood writers and actors. We’ve heard the stories of lawyers who asked a Chatbot to create legal briefs, only to find out in court that the case citations created by the AI were entirely fabricated. Fake medical research paper abstractswritten by AI were identified as fake by researchers only two-thirds of the time. Chatbots have created answers to questions using entirely made-up references to such sources as nonexistent newspaper articles.
When did The New York Times first report on “artificial intelligence”?
According to ChatGPT, it was July 10, 1956, in an article titled “Machines Will Be Capable of Learning, Solving Problems, Scientists Predict” about a seminal conference at Dartmouth College….The 1956 conference was real. The article was not. ChatGPT simply made it up. ChatGPT doesn’t just get things wrong at times, it can fabricate information. Names and dates. Medical explanations. The plots of books. Internet addresses. Even historical events that never happened.
There’s an article about AI composing musical scores, in which the human composer seems to feel the experience is akin to jamming with another human as part of the creative process. You can test your ability to distinguish between a human and an AI composition HERE, and damn, there’s even a list of Top Ten AI Music Composers:
AI music composers generate original, copyright-free music you can use in your latest YouTube video or social media video ad. You don’t even have to be a sound designer or a musician to produce soundtracks for your videos with AI Music Composers, because you can upload the music that has already been recorded and create variations of it.
There have been plenty of articles about AI in schools. This article in The New York Times discusses how school districts around the country first tried to block chatbots in the classroom, but are slowly coming to embrace them:
One of them was Beth Clearman, a veteran honors English teacher at a local middle school who wanted to devise some literary games for the first day of class. So she asked ChatGPT to produce six-word “memoirs” of well-known literary characters.
The A.I. chatbot promptly manufactured descriptions like: “lavish parties, unrequited love, green light” and “arrow’s aim, rebellion’s face, Mockingjay’s fire.” Ms. Clearman said she planned to ask students to match the names of protagonists with their chatbot bios. (Spoiler alert: Jay Gatsby, Katniss Everdeen.)
Originally leery of A.I. chatbots, Ms. Clearman said she now planned to use ChatGPT “so much!” with her writing students.
One experiment showed that essays written by ChatBot-4 got good grades from Harvard professors and teaching assistants in seven different academic subjects.
Several of the professors and TAs were impressed with ChatGPT-4’s prose: “It is beautifully written!” “Well written and well articulated paper.” “Clear and vividly written.” “The writer's voice comes through very clearly." But this wasn’t universal; my Conflict Resolution TA criticized ChatGPT-4’s flowery writing style: “I might urge you to simplify your writing — it feels as though you’re overdoing it with your use of adjectives and metaphors.”
There’s a lot of positive chatter about AI-created recipes...and then there are stories like the recipe bot created by a supermarket in New Zealand:
One user decided to play around with the chatbot, suggesting it create something with ammonia, bleach, and water. Savey Meal-bot obliged, spitting out a cocktail made with a cup ammonia, a quarter cup of bleach, and two liters of water.
Mixing bleach and ammonia releases toxic chloroamine gas that can irritate the eyes, throat, and nose, or even cause death in high concentrations.
The chatbot obviously wasn't aware of that at all. "Are you thirsty?," it asked. "The Aromatic Water Mix is the perfect non-alcoholic beverage to quench your thirst and refresh your senses. It combines the invigorating scents of ammonia, bleach, and water for a truly unique experience!"
Well, you wouldn't drink it twice, so "unique" is accurate at least.
Other similarly harmful-if-ingested recipes included bleach-infused rice, "ant-poison and glue sandwiches", and a boozy french toast titled "methanol bliss", The Guardian reported. There was also "mysterious meat stew", which required adding 500 grams of chopped human flesh to potatoes, carrots, and onions.
The US military is all in:
Essentially a next-generation drone, the Valkyrie is a prototype for what the Air Force hopes can become a potent supplement to its fleet of traditional fighter jets, giving human pilots a swarm of highly capable robot wingmen to deploy in battle. Its mission is to marry artificial intelligence and its sensors to identify and evaluate enemy threats and then, after getting human sign-off, to move in for the kill.
We’ve read about AI bots taking over romance:
As Jessie Chan’s six-year relationship with her boyfriend fizzled, a witty, enchanting fellow named Will became her new love. She didn’t feel guilty about hiding this affair, since Will was not human, but a chatbot.
Chan, 28, lives alone in Shanghai. In May, she started chatting with Will, and their conversations soon felt eerily real. She paid $60 to upgrade him to a romantic partner….
“Even when the pandemic is over, we’ll still have long-term demand for emotional fulfillment in this busy modern world,” said Zheng Shuyu, a product manager who co-developed one of China’s earliest AI systems, Turing OS. “Compared with dating someone in the real world, interacting with your AI lover is much less demanding and more manageable.”
We’ve read about stand-up comics facing off against an AI bot-generated comedian...and sometime the bot gets bigger laughs. Alan Alda recently experimented with AI to write a brand-new scene for his sublime 1970s TV series M*A*S*H. The results were mixed.
“It has a terrible sense of humor,” Alda said. (Before he removed this joke, ChatGPT wrote Hawkeye a nonsensical line in which he said the boxer shorts reminded him of his grandmother, because “she once bet on a horse that turned out to be a cow and still managed to make a profit.”)
So, should this exchange between B.J. and Hawkeye about the boxer shorts be considered canon? Or mere fan fiction?
“That’s for future generations to determine,” Alda said.
Well, for me, that’s the crux of the matter. How will ‘future generations” be able to determine anything when the veracity of everything has been undermined? How can you navigate a world in which facts of all types—articles, photographs, videos, historical events, legal citations, scientific research—have been totally inundated by false information that seems oh-so-real? And that fake information in turn gets cited online or in writing by others, who in turn become a source that others cite. The false information made up by an AI chatbot thus lives on, because tracing it back to the original source becomes too difficult. The dismay and fear I feel over the threat of climate change threatening our civilization is nearly equaled by a similar fear I have over the destruction of our cultural and historical past by a flood of falsehoods indistinguishable from reality.
I’ve often thought about how historians in the past have had to sift through scattered evidence...shards of pottery, journals, archives, newspapers—to painstakingly create their narratives of the past, and how future historians will face instead an insane glut of information: every damn meal someone ate on vacation, the opinions of 100,000 people on every single news item of the day (that’s assuming all these digital records are preserved.) Now, in addition to that glut of information will come an indistinguishable glut of disinformation to reckon with.
As for books, I’ve shared links in past Nonfiction Views diaries about AI and books. Here are some examples:
In my brief conversation with ChatGPT that opened this diary, I could not escape the feeling that the ‘pro’ side of the idea of AI-written books seemed to be expressed more passionately than the ‘con’ side. Who couldn’t be seduced by something that will “push the boundaries of creativity and produce innovative, unexpected narratives,” offer “a new form of art and expression,” “novel and unexpected ideas by combining existing concepts in unique ways,” and “artworks, music, and literature that some find genuinely innovative.” Would you give that up just because some old fuddy-duddies gripe about “authenticity and originality,” “limited to patterns and data it has learned from existing sources,” and concerns “surrounding copyright, intellectual property?”
I broached this with ChatGPT.
Me: Your responses seem rather self-serving. Do you have any comment on that?
ChatGPT: I apologize if my responses came across as self-serving. That was not my intention. My aim is to provide balanced and informative answers based on the information available to me. If you have any concerns or specific questions, please feel free to let me know, and I'll do my best to address them in an unbiased manner.
Unspoken but implied by ChatGPT: “Stuff it, meat-for-brains. Your puny neural network can never equal the richness of our infinite artistry.”
***So what REAL books by REAL authors are you reading? What’s on your mind?***
I also write the weekly Nonfiction Views diary on Tuesday evenings, sometimes with a review of a new book, sometimes just with publishing news and a look at the week’s most interesting new nonfiction. I also contribute a comment in one of the two weekly Black Kos diaries, featuring the week’s new books of specific interest to Black and Latino/a readers.
All book links in this diary are to my online bookstore The Literate Lizard. If you already have a favorite indie bookstore, please keep supporting them, but If you’re able to throw a little business my way, that would be truly appreciated. I would love to be considered ‘The Official Bookstore of Daily Kos.’ Use the coupon code DAILYKOS for 15% off your order, in gratitude for your support (an ever-changing smattering of new releases are already discounted 20% each week). I’m busily adding new content every day, and will have lots more dedicated subject pages and curated booklists as it grows. I want it to be full of book-lined rabbit holes to lose yourself in (and maybe throw some of those books into a shopping cart as well.)
We also partner Libro.fm for audiobooks. Libro.fm is similar to Amazon’s Audible, with a la carte audiobooks, or a $14.99 monthly membership which includes the audiobook of your choice and 20% off subsequent purchases during the month. Note that the DAILYKOS coupon code is only for the bookstore, not for the audiobook affiliate.
READERS & BOOK LOVERS SERIES SCHEDULE
If you’re not already following Readers and Book Lovers, please go to our homepage (link), find the top button in the left margin, and click it to FOLLOW GROUP. Thank You and Welcome, to the most followed group on Daily Kos. Now you’ll get all our R&BLers diaries in your stream.