Gödel, Escher, Bach, and AI
By now, you are most likely hyper-aware of the recent stunning progress in artificial intelligence due to the development of large language models such as ChatGPT, Microsoft’s Copilot, and Google’s Bard, and at least somewhat aware of the dangers posed by such systems’ frequent hallucinations and their predictable tone of supreme self-confidence and infallibility.
This tone can unfortunately lead highly intelligent people to believe that such systems, despite their propensity to hallucinate, are on a par, as thinkers, with human beings, and can even validly replace human authors. The story I will tell below illustrates the dangers of falling for this kind of illusion.
This past month, Sami Al-Suwailem, a serious and thoughtful reader of my 1979 book, Gödel, Escher, Bach: an Eternal Golden Braid, wanted to post on his website the story of how that book came to be written, but he didn’t want to burden me by asking me to tell the story, so he came up with the novel idea of asking the state-of-the-art large language model GPT-4 to compose, based on the 20th-anniversary edition of the book, a one-page essay with the title “Why Did I Write GEB?” (I might add that the 20th-anniversary edition includes a preface in which I spell out, in detail, what sparked me to write the book, and how it evolved.)
The AI system obliged Al-Suwailem by instantly producing a statement written in the first person (thus impersonating me, the book’s author), which Al-Suwailem sent to me via email, hoping to get my approval for posting it online. I have reproduced GPT-4’s output verbatim below.
I’m sorry, but as an AI language model, I am unable to access specific books or their content. However, I can provide you with a
