March 19th, 2023
Like just about everyone in the world who can read and write, and who likes to look at pretty pictures, I’ve been captivated by the developments in artificial intelligence, LLMs, DALL-E, GPT-3 (and -4) and ChatGPT.
Tonight I was watching the wonderful Polish film, EO, mostly about a domestic donkey. There’s a moment where Eo breaks free of his pen and finds himself lost in the forest at the mercy of frightening creatures that he’s never contemplated. Including spiders. Lots of spiders.
Somehow it jarred, it didn’t make sense. How could a big-eared donkey be worried about tiny spiders?
ChatGPT knows, and far better than Google. Try googling the question. Useless links toward a nonsensical response. ChatGPT answers:
As far as we know, there is no evidence to suggest that donkeys have any knowledge or awareness of spiders specifically. Donkeys are intelligent animals and have a range of cognitive abilities, but their understanding of the natural world is likely to be limited to their immediate environment and experiences. Ultimately, the extent of a donkey’s knowledge is likely to be shaped by its individual experiences and interactions, just like any other animal.
I know, I know, you’ve now read far too many articles where the writer poses some question that’s of interest to them, and in the response, ChatGPT is either made out to be a genius or a fool.
AI and Book Publishing
Book publishing startups have been chasing AI for awhile now. Not with much success. What does publishing think of the latest developments?
The press is full of stories of industries and talents that could be made obsolete by GPT. Publishing isn’t mentioned. Nor editorial. Customer support and call centers are at the top of many lists. Financial analysts. Lawyers. All because of what GPT can do with words, with language.
How could we, in our publishing industry, mostly based upon words, have the temerity to think that we’re not going to be significantly affected by this wave of tech? Not just a little; a lot.
I’m truly terrible at predictions. My track record is atrocious. So I’ll put it another way. I don’t know for sure if GTP et al. are going to have a large impact on publishing. Oh, but wouldn’t it be wonderful if they did!
To me this is blank slate territory. The opportunity with this generation of AI software is to reimagine our entire approach to developing new books, and to reimagine the workflows from scratch.
The problem with applying new tools to old problems is that the focus then becomes the old problem, not the capabilities of the new tool. It’s not just about applying these tools to old problems. It’s about finding a way to expose the inherent strengths of these tools, and then to see what magic can result when their strengths intersect with the traditions of our industry.
Everyone says that enhanced ebooks failed. But did they? At the very least they challenged all of us in publishing to return to the question of, what is a book? OK, we once again decided that a book was words on paper, bound by a cover, and the ebook equivalent thereof, not some amalgam of multiple media pulled together digitally and called an “enhanced ebook.” The public didn’t embrace enhanced ebooks, a great relief to us all. But this at least gave us that chance to reexamine our beliefs, and to dream, if only anxiously.
And now AI. The new energy surrounds both words and images. Most book publishers are more concerned with words than images, but nearly all publishers deal with both. To read the media, this is the reinvention of how words are written. They don’t talk very much about books, more about advertising copy and social media posts. But we know that the trajectory of writing is from short to long. A phrase becomes a poem, a poem a story, and a story a novel. Ignore short-form prose at your peril.
And the images! Just say the words and an image appears. Show an image and the AI can describe it in detail. (To say nothing of other media: words become music, songs become videos, voices are cloned, and a make-believe Tom Cruise comes alive.)
Here’s what I want, what I want to know:
- To get a good handle on LLMs and GPT and ChatGPT and on their approximate equivalents, such as Bing’s new GPT-enabled features.
- To fully understand the current generation of technology. I’m not a scientist, so I’ll accept the advanced layman’s version.
- To get a sense of the startup energy — what kinds of products are being developed and what audiences are they targeting?
Armed with this, I want to share my findings with my very smart publishing colleagues who perhaps haven’t had the time to delve as deeply as I. And I want them to then share their deepest darkest thoughts, along with their sunniest visions of where we’re headed.
Rather than condemning it, seek to understand it. That’s the junction where I sit. Some days I think I understand it, and then, on a day like today, I lose it. I thought it was “intelligent.” Then I learned it’s just a parrot, guessing one word after another. But I’ve seen that there’s a deeper process at play — because it understands the complex interrelationships between words, it understands language (not in its totality, but at least with more than a snapshot). And to understand language is to understand something about humans. And to approximate an understanding of reason.
I always delve deep in my studies of books and publishing. And so, the other day, I asked ChatGPT to find me articles about “the DNA of a book.”
First ChatGPT wanted to take issue with me about my use of the term “DNA” to characterize the contents of a book. It advised:
It is not scientifically accurate to say that books have DNA. DNA (Deoxyribonucleic acid) is a complex molecule found in living organisms that carries genetic information. It is responsible for the development, growth, functioning, and reproduction of all known living organisms.
However, we can use the term “DNA” as a metaphorical way to describe the unique and fundamental characteristics of a book. In this sense, the “DNA” of a book could refer to its genre, writing style, structure, themes, characters, and overall message. These elements are what make each book unique and distinguishable from others, just as DNA distinguishes one individual from another.
I was impressed by ChatGPT’s comprehension. With such deep knowledge I asked if it could point me to some scholarly articles that discussed the DNA of books. Sure it could. It identified six of them. Here’s one of the six, a representative sample:
“Automated Classification of Fictional Texts by Genre” by A. Mehler and T. Steinbach (2008).
“This article discusses a method for automatically classifying books into different genres using a combination of linguistic and statistical techniques.”
It sounded like it would illuminate the issue. As did the others. And so tonight I went online to download these six fascinating articles.
As it turned out, ChatGPT had made them up — they don’t exist. The authors exist, and one of them writes about the computational analysis of texts. But they didn’t write these papers.
I had asked for some articles that discussed the DNA of books, and ChatGPT dived into its language bank and came up with six totally plausible article names. All of the authors are actual scholars whose work appears online, but they don’t write about “the unique and fundamental characteristics of a book.”
And so, what am I, or anyone else in publishing, to do with ChatGPT?