Tag Archives: Artificial Intelligence

John Buchan and AI

As a lover of the works of John Buchan and one not unconcerned about the precarious future of this planet I consulted ChatGPT using a famous and prescient quote by Buchan from his thriller The Power House (1916).

I asked them this: “John Buchan wrote in 1916 “ ..you think that a wall as solid as the Earth separates civilisation from barbarism. I tell you, the division is a thread,a sheet of glass. a touch here, a push there, and you bring back the reignof Saturn.” Is this still true in 2023?” 

25 seconds later they replied: “The quote by John Buchan is certainly still relevant in 2023, as the line between civilization and barbarism remains thin and fragile. Though the world has made great strides in terms of technological advancements, social progress, and global connectivity, there are still forces that work to destabilize these achievements and push society back towards chaos and conflict. Whether it’s geopolitical tensions, economic inequality, racial divides, or environmental degradation, the challenges facing humanity require us to remain vigilant and work together to maintain and strengthen the bonds of common humanity that hold us together. In short, the quote from John Buchan remains a timeless reminder of the need for vigilance, empathy, and unity in the face of adversity.”

A good answer. He/she / it is definitely more Bernie Sanders than Logan Roy. I went on to ask it for a parody of John Buchan. In a past Jot we have a very good Buchan parody by a young girl at boarding school in the 1930s. It is many miles better than Chat’s brave effort. As the old unreconstructed Dr Samuel Johnson said (in about 1760) of women preachers: “Sir…(it)is like a dog’s walking on his hind legs. It is not done well; but you are surprised to find it done at all.” Tune in again soon to see both parodies..

The Beatnik Poet Machine

Screenshot 2018-12-28 11.02.57Found in an old LIFE magazine from March 3 1961 this computer story:

In  Glendale California a certain computer even thinks it is a beatnik poet. Having been taught a few rules of grammar and given a vocabulary of 500 words of the type that  beatnik poets frequently employ, this robot has clanked out works such as the following:

Auto beatnik poem number 41: Insects

“All children are small and crusty,

An iron can saw all dragons,

All pale, blind, humble waters are cleaning,

A insect, dumb and torrid (torpid) comes off the Daddy-o,

How is a insect into this fur?”

Some auto beatnik poems were read by a bearded scientist to unsuspecting denizens of a Los Angeles coffeehouse who ‘became quite stirred up with admiration.’ One especially appealing line , which the computer likes, is “AH, I AM NOT A MACHINE.”  The beatnik computer is not a stunt. Its masters are using it to study how to build better computers that can communicate in the English language.

This story is repeated with the variant word “torpid’ for ‘torrid’, possibly an improvement, in the 1962 book Science Shapes Tomorrow (Phoenix, London). They quote the poem in a chapter asking whether computers can think. They say that if a computer is going to think they must be able to do four main things:

  1. They must be able to learn by experience.
  2. They will have to become more flexible. The machine will have to come far closer to our almost miraculous five senses which feed our brains with information – great steps are being made in this direction ..the Perceptron is being taught to recognize letters of the alphabet even if they are sloppily written…
  3.  A the moment most machines work on strictly logical lines -they will have to break free to produce for themselves new and original ways of working with the data inside them.
  4.  The machine must be able to recognize when it is  being brilliant. Any machine fed with enough words and grammatical rules, for example can write poetry. It could even write very good poetry – another Shakespeare sonnet, perhaps, but the machine is not a great poet until it can distinguish the perfect sonnet from the drivel. And the same goes for  logical thinking- it must be able to recognise which of its logical statements are valuable and which are not, even though all of them are true. It would be sad if a machine, for example, hit on the successor to Einstein’s theory of relativity and then did not recognise  that this was a more valuable statement to make than printing out that the earth is round.. the complete answer to mankind problems might find itself crumbled up in the wastepaper basket…