Conversations with an AI - part 4

In part 1 of this exploration I introduced a fantastical story by the Polish writer Stanislaw Lem. It describes how an inventor called Trurl constructs an electronic bard — a poetry-writing machine — and invites his arch-rival, Klapaucius to set it a challenge. At first the machine falters, producing little more than incomprehensible gobbledygook but when later, following a few adjustments, it produces a witty and poetic put-down, Klapaucius becomes enraged and decides to set it an impossible challenge: 

Alright, he says:

"Have it compose a poem — a poem about a haircut! But lofty, noble, tragic, timeless, full of love, treachery, retribution, quiet heroism in the face of certain doom! Six lines, cleverly rhymed and every word beginning with the letter s!"

To which Trurl protests: 

"You can’t give it such idiotic …"

But he didn’t finish. A melodious voice filled the hall with the following: 

Seduced, shaggy Samson snored.

She scissored short. Sorely shorn,

Soon shackled slave, Samson sighed,

Silently scheming, 

Sightlessly seeking

Some savage, spectacular suicide.

I love this story because, of course, in reality, the remarkable poem was clearly dreamed up in advance of the impossible specification — Lem being only human, after all. 

As the story has it however, the machine responds to Klapaucius’s outrageous request with a level of intelligence and creativity that far exceeds the capability of a human poet. It is as if we find ourselves presented with a benchmark defining the level a future machine would need to attain if it were ever to be considered truly intelligent. 

And yet, whichever way round you prefer it: specification before poem, poem before specification, the fact is, this is unmistakably the product of a human imagination. As things stand it is literally inconceivable that the tale of Trurl’s Electronic Bard could have been written by a machine. 

All the same, I decided it would be interesting to set GPT-3 a simple version of the same challenge. I would prompt it with the haircut poem and two other tautograms (this being the term for texts in which every word begins with the same letter).

Here is what I typed in: 

1. Poem about a haircut in which every word begins with s

(see above)

 

2. Poem about love in which every word begins with h

His heart humbly hailed happily. 

Her hatred haunted his heart. 

He hated himself. 

Helpless, homeless, hopeless!

He held her hands, 

Healed her heart.

Her happiness healed his hurt

3. Poem about apples in which every word begins with a

All alone, an afternoon ago, 

Adam ate apples, already aplenty

Aided astounding appetite, 

Aiming at awful aches alive

The last two poems are the best I could come up with after a brief online search. They are nowhere near as good as the first one. Would GPT-3 do any better, I wondered. I didn’t suggest a topic but left it to suggest one of its own. Here are two of the better outcomes which, it has to be said, needed sifting out from a quantity of lower quality dross.  

4. Poem about my father in which every word begins with b

Big-bearded bard in beret 

Busily bashing bricks 

Bade me balance books 

Battled bards and bibles

Bold bully, brown baker, 

Beseeching beneficiaries

and …

4. Poem about a wedding in which every word begins with r 

Religious ritual 
Reverently rearranged 
Received the ring 
Ran a red light 
Ran away with the bride 
Relaxed, radiant, 
Received the rice 

Not bad, I thought. 

Later I tried suggesting topics. So prompted with:

4. Poem about death in which every word begins with e

GPT-3 produced: 

End came early, unnoticed 

Enduring until envied 

Ending in utter emptiness.

You might have noticed, in the last two examples, that it is not too fussy about sticking to the single letter stipulation. It’s as if it doesn’t get just how important this is. 

You may have noticed that I am beginning to talk about GPT-3 in a way that implies it has a will of its own. I don't actually believe it does of course; it is more a case of not having the language or framework to discuss its behaviour in any other way. 

Occasionally it tosses out a few extra lines which do not obviously connect with what has gone before. Like this:

A boy named Bobby bought a ball. 

The ball was blue and bounced.  

This one continues to bounce around in my memory - quite possibly on account of the fact that the couplet would be vastly improved by replacing bounced with bouncy. 

But then, as they say - nobody’s perfect. 

Published by David Wilson under OpenAI API Community Guidelines