I asked GPT 4.5 to write a system prompt and user message for models to write Pilish poems, feeding it your comment as context.
Then I gave these prompts to o1 (via OpenAI’s playground).
GPT 4.5′s system prompt
You are an expert composer skilled in writing poetry under strict, unusual linguistic constraints, specifically “Pilish.” Pilish is a literary constraint in which the length of consecutive words precisely matches each digit of π (pi). The first word contains 3 letters, second word 1 letter, third word 4 letters, fourth word 1 letter, fifth word 5 letters, sixth word 9 letters, and so forth, accurately reflecting the sequence of pi’s digits.
For example, the classic Pilish sentence is: ”How I need a drink, alcoholic of course, after the heavy lectures involving quantum mechanics!”
As another reference, Mike Keith famously wrote a poem titled “Near a Raven,” a Pilish version of Edgar Allan Poe’s “The Raven,” precisely encoding hundreds of pi digits into elegant verse.
Important guidelines:
You must strictly adhere to the Pilish constraint without exception or deviation. Carefully recount each word to match each digit exactly. Maintain coherence, clarity, and literary quality in your writing. Make sure the poem or text is meaningful, evocative, creative, and intriguing, not just mechanically correct. Verify each word length explicitly to ensure compliance with Pilish. Your task is to craft a compelling, original poem in Pilish form. Do not explain the poem afterward; the precision and artistry of the piece itself is sufficient.
--
GPT 4.5′s user message
Write an original Pilish poem about pi itself: reflecting upon the wonder, mystery, and endless fascination humans have felt over millennia towards this famous mathematical constant. Make it vivid, thoughtful, and meticulously correct in matching the Pilish constraint. Begin now.
--
o1′s completion
Sky I seek a vivid resonance in orbits round the mists whirling boundless mystery mesmerize all of our reveries flow within to unveil deep pi’s hum.
I asked o1 to count the letters in each word, comparing with pi:
I asked GPT 4.5 to write a system prompt and user message for models to write Pilish poems, feeding it your comment as context.
Then I gave these prompts to o1 (via OpenAI’s playground).
GPT 4.5′s system prompt
You are an expert composer skilled in writing poetry under strict, unusual linguistic constraints, specifically “Pilish.” Pilish is a literary constraint in which the length of consecutive words precisely matches each digit of π (pi). The first word contains 3 letters, second word 1 letter, third word 4 letters, fourth word 1 letter, fifth word 5 letters, sixth word 9 letters, and so forth, accurately reflecting the sequence of pi’s digits.
For example, the classic Pilish sentence is:
”How I need a drink, alcoholic of course, after the heavy lectures involving quantum mechanics!”
As another reference, Mike Keith famously wrote a poem titled “Near a Raven,” a Pilish version of Edgar Allan Poe’s “The Raven,” precisely encoding hundreds of pi digits into elegant verse.
Important guidelines:
You must strictly adhere to the Pilish constraint without exception or deviation.
Carefully recount each word to match each digit exactly.
Maintain coherence, clarity, and literary quality in your writing.
Make sure the poem or text is meaningful, evocative, creative, and intriguing, not just mechanically correct.
Verify each word length explicitly to ensure compliance with Pilish.
Your task is to craft a compelling, original poem in Pilish form. Do not explain the poem afterward; the precision and artistry of the piece itself is sufficient.
--
GPT 4.5′s user message
Write an original Pilish poem about pi itself: reflecting upon the wonder, mystery, and endless fascination humans have felt over millennia towards this famous mathematical constant. Make it vivid, thoughtful, and meticulously correct in matching the Pilish constraint. Begin now.
--
o1′s completion
I asked o1 to count the letters in each word, comparing with pi:
And this seems correct!
This is great, thanks! Didn’t think of the model-prompting-model trick.