24,483 Dreams of Death
A Film Experiment
Run Time: 14m 52s
Can an A.I. be creative?
With machine-generated imagery and narration, 24,483 DREAMS OF DEATH gives us a glimpse into our world as seen by a new intelligence of our own design.
REVIEWS
“Hypnotic masterpiece is the result of an experiment to have an AI create a visual world while watching a Mario Bava film for six days. The narration is the poetry the AI created.
A dream within a dream within a dream.
I can not explain this film or what it does - I can only point you toward it, tell you turn off all the lights and watch this as big as possible as it etches itself on your psyche.
I have no idea if it means anything but god damn it is one of the great film experiences of the year that had me emailing my friends.
A must see at Slamdance or where ever you find it.”
— Steve Kopian, Unseen Films
Background
During the spring of 2020, a machine intelligence spent six days watching the film La Maschera del Demonio. Starting as a blank slate, the A.I. received its entire knowledge of our visual world from this Mario Bava classic.
This film is a record of the machine's neural network forming in real time, not footage in the traditional sense of photographed scenes, but footage of the internal experience of a new intelligence learning about our world for the first time.
Unfortunately, to create the footage it was necessary to sequentially create 24,483 neural networks or “miniature brains” and then, after they had served their purpose, immediately destroy them.
To complete the experiment, a separate A.I. was used to write the poetry heard in the narration. In a single eighteen hour period the machine wrote 1,623,811 words of poetry, nearly 100 books worth. Surprisingly, much of it was on the subject of death and loss.
Why did the machine write so many death themed poems? It is likely the machine was simply creating a pastiche of the nineteenth century poetry it had read during training.
It is frankly impossible that the machine was referring to the destruction of the 24,483 neural networks used to create this film...
