by Kenneth Francis (December 2025)
In the past year, many musicians and artists are quite concerned that AI will plagiarise or replace their work and livelihoods.
London’s AP News reported that musicians from ABBA, Radiohead and The Cure have joined actors and authors in signing a protest letter against the mining of their artistry to build artificial intelligence tools.
It said that thousands of artists signed the letter [in October 2024], the latest public warning about AI tools that can spit out synthetic images, music and writings after being trained on huge troves of human-made works.
Following on from this, in an article last month in Sky News, by technology correspondent Rowland Manthorpe, such fears by singers and writers are growing rapidly in the literature community and beyond, according to a new survey.
The findings show that 85% say they think their future income will be negatively impacted by AI, and 39% claim their finances have already taken a hit.
Tracy Chevalier, the bestselling author of Girl With A Pearl Earring and The Glassmaker, shares that concern.
She said: “I worry that a book industry driven mainly by profit will be tempted to use AI more and more to generate books … If it is cheaper to produce novels using AI (no advance or royalties to pay to authors, quicker production, retainment of copyright), publishers will almost inevitably choose to publish them.”
She added that if they are priced cheaper than ‘human made’ books, readers are likely to buy them, the way we buy machine-made jumpers rather than the more expensive hand-knitted ones.
The University of Cambridge’s Minderoo Centre for Technology and Democracy asked 258 published novelists and 74 industry insiders how AI is viewed and used in the world of British fiction.
Alongside existential fears about the wholesale replacement of the novel, many authors reported a loss of income from AI, according to survey, which they attributed to “competition from AI-generated books and the loss of jobs which provide supplementary streams of income, such as copywriting”.
However, in my opinion and that of a popular AI bot, not all genres are at risk of AI replacement. Recently, I’ve written two collections of fictional short stories in the Absurdist/Surreal genre, and when I asked ChatGPT the following question, the answer was comforting. I asked: Can AI replace Absurdist literature?
That’s a thought-provoking question! On one hand, AI can certainly generate absurdist literature, in the sense of producing texts that mimic the surface level of absurdist themes: nonsensical situations, bizarre characters, illogical dialogue, and so on. However, the deeper question is whether AI can replace or capture the essence of what absurdist literature represents.
Absurdism is about more than just randomness or disjointedness; it deals with profound existential themes—like the search for meaning in a meaningless world, the tension between rationality and the irrational, and the absurdity of human existence. Writers like Albert Camus, Franz Kafka, and Samuel Beckett explored these ideas in ways that resonate deeply with readers because of their lived experiences and their own existential reflections. Absurdist literature often grapples with the human condition in a way that evokes an emotional, intellectual, or even spiritual response. [But ultimately] AI, while capable of simulating absurdist narratives, doesn’t experience absurdity. It doesn’t question existence or feel the anxiety or despair that absurdism explores. So, in a sense, AI can produce works that look like absurdist literature, but it lacks the philosophical depth that comes from the writer’s personal encounter with absurdity. —ChatGPT answer
The same applies to my non-fiction work, where I sometimes analyse the hidden grammar and semiotics in the narratives, marinated in semantics and nuance. For example, in two of my recent books, Theology in Film, and Theology in Music (En Route Books and Media), I deconstruct many things in song and film that have previously not been mentioned in literary criticism prior to their publication. But post-publication, if such analysis is picked up by an AI programmer, the inputs for future bot responses might be influenced by my hitherto exposure of such narratives.
Finally, I highly recommend downloading, on YouTube, Anthony Burgess’s Lots of Fun at Finnegans Wake (1973). In the monologue, Burgess explores and deconstructs elements of the famous complex book by James Joyce. It is difficult, if not impossible, to imagine AI discuss this in a superior way to Burgess’s incredible analysis. When I first attempted to read Finnegans Wake some 40 years ago, I gave up quarter-way through the book because of the absurdity of the text due to Joyce’s stream of consciousness narrative—AI, eat your non-existent heart out!
Table of Contents
Kenneth Francis is a Contributing Editor at New English Review. For the past 30 years, he has worked as an editor in various publications, as well as a university lecturer in journalism. He also holds an MA in Theology and is the author of The Little Book of God, Mind, Cosmos and Truth, The Terror of Existence: From Ecclesiastes to Theatre of the Absurd (with Theodore Dalrymple), and Neither Trumpets Nor Violins (with Theodore Dalrymple and Samuel Hux). His most recent books are Theology in Music: How Christian Themes Permeate Classic Songs, Theology in Film: How Christian Themes Permeate Classic Movies, and Cities of the Absurd: Strange Tales from the Dark Metropolis.
Follow NER on Twitter @NERIconoclast
One Response
The short to medium term consequences are devastating.
I would suspect the publishing industry would very well try to automate book and all manner of creative endeavours. Of course they’re going to do that, and I would imagine they are already doing so.
>But post-publication, if such analysis is picked up by an AI programmer, the inputs for future bot responses might be influenced by my hitherto exposure of such narratives.
It’s not individual programmers doing this — they just end up working for large corporations with vast networks dedicated to harvesting everything. Potentially, the moment a works hits the internet it can be web-scrapped and its “essence” sucked dry to feed the “models” (AI).
Depressing, isn’t it?
However, as well as grifting human generated content that some poor sod has poured effort into, the AIs will also be sucking up vast quantities of previously machine generated content that others have simply gone to Chat-Jipperty as said, “Make me XYZ”, and then stuck it online. Youtube is now flooded with AI created videos that have been both written and narrated by machine. It can sometimes be very hard to discern a real video from a synthetic one.
For example, this one is not only fake but impersonating a real individual:
https://www.youtube.com/watch?v=fyTZngp4l_c
From this moment on, the only way to discern is to judge by the “fruits of the labour”.
Ultimately, as I have written, the upshot of all this is the equivalent of a perpetual motion machine, the wheels of which will gradually(*) come off in a flood of emptiness and lies.
The long term may be brighter, as those who can truly create new paradigms will be extremely valuable. Whether or not they will be allowed to know their true worth will be another question.
(*) I lament the nature of software. If only “wheels came off” suddenly and you crashed and burned — and everyone could see that the project has failed. But that’s not what happens. Instead, things degrade and fail gradually, but everyone’s too invested to take a step back. Enough rope and all that…