Ask HN: How do you make AI writing usable?

4 points by david_shi 10 days ago | 7 comments

Every time I ask the latest models to write something, it defaults to LLMisms like contrastive negation and long unnecessary lists.

Is there a way to desloppify AI writing, or is this just the new status quo?

bloomfieldj 10 days ago |

This is a helpful resource your AI can reference, though each model has its own inherent style and preferences: https://tropes.fyi/tropes-md

david_shi 9 days ago | |

Ah this is very helpful. I've been pointing out things that the model does, labeling it, and then adding them into a skill.

The models (Opus, etc) are very good at labeling the pattern when I point it out, but if I don't prompt it beforehand it responds like a host from Westworld.

https://www.youtube.com/watch?v=UTZ6Lvh5gL4

verdverm 10 days ago |

Instead of having it do the writing, use it as an assistant (research, sample text) and then pick good parts and write it yourself. Examples of your/good writing are indispensable

Depends on who you are writing for too

david_shi 9 days ago | |

Yeah. I'm realizing that the models are strong at drafting the overall shape of the writing but the specific phrases are grating once you've seen it hundreds of time in slop.

verdverm 9 days ago | | |

There is some advice that goes something like "read more to get better at writing"

codemax98 10 days ago |

Models follow examples far better than instructions. "Write like this:" with examples

david_shi 9 days ago | |

Even with the examples, I've found that explicitly pointing out what not to do is moderately helpful if the model is given some time to self-evaluate. I wish this was something that came out of the box though.