〽️arat
Oli"A common fallacy is to assume authors of incomprehensible code will somehow be able to express themselves lucidly and clearly in comments."
– @kevlin
"... or prompts." I would like to add.
Julian Andres Klode 🏳️🌈@oli the way it works is you write the comment, signature, then hit autocomplete to let the LLM write the function body, and then you adjust the comment and regenerate until it does what you want.
The comment *is the prompt*