GPT-4 and ‘The Great Automatic Grammatizator’

I recently read Roald Dahl’s short story The Great Automatic Grammatizator (published in 1954) and was struck with the parallels to the technology we have available to us today in generative AI, and in particular the large language models such as GPT-4. You can read the full text online.
In the spirit of experimentation, I prompted GPT-4 to write an article reflecting on how the story is predictive of generative AI functionality. Here is the result. with formatting applied but no editing.

Title: The Precursor to Contemporary AI in Roald Dahl’s “The Great Automatic Grammatizator”

Introduction:

The proliferation of artificial intelligence (AI) applications in the contemporary era of digital technology is often depicted in popular science fiction, but few anticipate that such themes may have found a place in classic literature. Roald Dahl’s work, “The Great Automatic Grammatizator,” is an example of such literature that predated the current discourse on AI by more than half a century. Dahl includes an imaginary machine that can write literary pieces by following procedural and computational rules. This eerily anticipates the functionalities of today’s generative AI — a predictive technology, now a reality in the world of machine learning, that can generate novel data in areas ranging from text, to music, to images, and beyond.

AI in the Literature—The Great Automatic Grammatizator:

In Dahl’s “The Great Automatic Grammatizator,” the protagonist, Adolph Knipe, a computational engineer, devises an automatic writing machine that can produce literary pieces with minimal human intervention. Dahl probes into the narrative of AI as an analogue to human intelligence, creativity and productivity, anticipating the societal impacts of the automation of intellectual labor. The automatic writing machine in Dahl’s narrative is capable of creating a vast number of stories and novels using pre-defined preferences, churning out entire literary pieces within seconds. Not unlike contemporary AI systems, it uses stored information (vast word lists and plot outlines) and applies a tightly defined set of rules (grammar and syntax) to generate its output.

Generative AI:

Generative AI, similar to Knipe’s creation, uses machine learning to generate novel data output based on an initial input. Generative pre-training, where models learn to predict the next word in a sentence, has been successful in generating high-quality, human-like text. The functionalities Dahl pre-empted now find themselves embedded in sophisticated technologies such as OpenAI’s GPT-4, proving Dahl’s insight to be more than mere fantasy.

The Great Automatic Grammatizator and Modern Generative AI:

Though the machine in Dahl’s story and modern AI use essentially different principles — the former using pre-set rules and the latter generally learning from examples and patterns in data — both capitalize on the process of generating complex information by traversing an underlying structure (namely, in language). Both also grapple with the balance of creativity and coherence. Though they can create text that is grammatically correct and logical, gauging its depth, humour and emotional impact can be challenging – among the biggest hurdles in the development of generative AI. Interestingly, Dahl’s machine was operator-guided, while contemporary technologies aim to be increasingly autonomous. Yet, they share an uncanny resemblance in their outcomes – the production of seemingly ‘human-like’ compositions.

Ethical and Societal Implications:

Dahl’s narrative also highlights the socio-economic implications raised by AI’s incursion into complex, traditionally human, domains such as literature. The monopolization of the literary market by Knipe’s machine mirrors concerns about AI affecting job security. The story paints a bleak picture for human authors, whose work is replaced with an unrecognizable, distanced, and manufactured form of artistic expression. Dahl grimly proposes a future where creativity is condensed to a series of mathematical procedures and the human touch in literature becomes obsolete – issues echoed in the AI ethics discourse today.

Conclusion:

“The Great Automatic Grammatizator” provides a prescient commentary on generative AI mechanisms. Dahl’s insightful critique on the automation of creativity underscores the importance of considering the broader societal and ethical implications of AI advancements. Whereas generative AI functionalities hold promise for transformative applications, their employment should be carefully considered, ensuring that uniquely human elements such as creativity and emotionality are not diminished in the process.