Comment by mediaman
3 hours ago
They’re not just trained on human prose. They’re sent to RLHF, and also their language changes as a result of RL on verifiable rewards.
Getting it to write well is really hard because there’s no real way to verify whether it’s good prose or not. You and I can tell, but we can’t write a verifier that codifies our judgment.
Maybe they’ll find a way to improve this, but for now it’s certainly one of the harder problems to solve for LLMs.
Part of it is that I think they also have poor theory of mind, which I imagine is also a hard thing to train it to do.
Why is it hard? Ask it to write professionally in mid-twentieth century style English, and without resorting to the clickbait style of writing.
In any event, other LLMs may not automatically have the problem, and don't even require such a prompt. This is a Claude problem.
I don’t think you realize how long ago the middle of the 20th century was.
What does the age of the style have to do with anything? You can ask them to write like Dickens or the King James bible or in Caesar's Latin, too, and these are even older.
1 reply →
I don't think you realize the prompt actually works. The word "style" does it. I guess you like clickbait too much.