“Return to the Water!” Shouted Hoot
All systems go! said grasshopper
PROMPT: All systems go
All systems go!” said grasshopper.
“Snout to a edges stake,” lawnhopper said.
“Wait here,” said Dr. Goody Tiptoes. “The day to kick-off.”
“Er,” shouted Nancy Twit.
“OK,” shouted Dr. Goody Tiptoes.
“Step in here, please,” demanded Mrs Twit.
“I don’t want to come to Ground NanDo*!” they shouted. “I don’t want to come to City
In but a minute!”
The display went upides
and down scrolls.
“Right. Return to the water!” shouted Hoot.
But Lowly had flown far ahead.
Years had come to see Cold headless
[END TRANSMISSION]
Editor’s Notes
Written by AI, using my random-temp script, and using my picturebooks model, which is a fine-tuning of gpt-2 774M. Chosen from among the other recently generated stories by me, a human. This one had a pretty hot temp (anything above 1.0 for this picturebook model gets pretty trippy and overcreative).
Prompt
“All systems go”
Came from one of these places, which the script chose at random from a list of phrases:
- https://randomwordgenerator.com/sentence.php
- https://fungenerators.com/random/idiom
- https://www.theidioms.com/
- https://www.be-a-better-writer.com/cliches.html
- https://gist.githubusercontent.com/signed0/d70780518341e1396e11/raw/2a7f4af8d181a714f9d49105ed57fafb3f450960/quotes.json
- https://www.phrases.org.uk/meanings/phrases-and-sayings-list.html
Edits
No edits made. It’s exactly as generated! :)
Title
Title was human-derived by me from the generated text
Plagiarism Checked
Plagiarism checked with Plagiarism-Basic against the dataset, looking for sequences 5 words long duplicated in both. It found none.
GPT-2 Settings
{
"return_as_list": true,
"length": 200,
"truncate": "<|endoftext|>",
"nsamples": 1,
"batch_size": 1,
"run_name": "model-picturebooks-run1",
"prefix": "All systems go",
"temperature": 1.3
}