Ask HN: How do you make AI writing usable?

4 ポイント投稿者 david_shi20 日前7 コメント

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?

7 コメント

bloomfieldj20 日前

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_shi19 日前

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

verdverm20 日前

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_shi19 日前

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.

verdverm19 日前

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

codemax9820 日前

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

david_shi19 日前

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.