Roughly, my algorithm will compute the probability of my writing some words in my texts, after Word 1 and Word 2. For instance, in my texts, after “It is”, let’s say there is a 10% chance of having “obvious”, 20% “raining”, 25% “a”, and so on. Thanks to this data my generator will choose words according to those probabilities. If my generator first chooses “It is” as the beginning of a sentence, there is a 10% chance the next word will be “obvious”, 20% “raining”, etc.
The resulting sentences are often funny, always very surreal.
Selected generated sentences:
“I will be me. I was twelve, the trend in art was realistic descriptions of the deep maze inside… Recovered memories suddenly propagate, What he recalls from her throws him in a modernist museum.”
“I got my blue eyes and my aunt and I gasped, alone and completely blind, fearing my nocturnal comrade had burnt itself, that only ebony ashes would be left from the bubble, everything seems so “normal” on this islet. Rocks, a tree, rocks, the Pacific ocean and some more rocks.”
“Trevor came back as expected. He should appear here in five minutes, now that I think I can see a mouse over his shoulder but as I tried to reach for a light I could see it scour a meadow. Now they were fleetingly superimposed and I feel embarrassed and proud at the center of the time gap. Humans are now going to bring sensors, appear in the future. Today, these efforts will finally succeed. New Orleans’ TimeWorm team members are on the right armrest while I should have found something by now… Minh says impatiently, as he is a big supporter of the bubble to prevent my shaking legs from making me fall.”
“Minkiewicz doesn’t even look away, I think about me, because I have hung it in the entomology volume. It definitely looked like a butterfly more than her long scarlet curls and her green eyes.”