Hacker News Reader

Exactly and this is hell for programming.

You don't know whose style the LLM would pick for that particular prompt and project. You might end up with Carmack or maybe that buggy, test-failing piece of junk project on Github.

View on HN

You can tell it who's style to copy, it's actually decent at following instructions like that.

My first experiments with LLM chat was to ask to produce text mimicking the style of a distinct, well-known author. It was also quite good at producing hybrid fusions of unique fictional styles, A + B = AB.

It's not bad at following my own style. I have longstanding quirks like naming any string that will end up in a DB query with a "q_" in front of the variable name, and shockingly Claude picks up on those and mimicks them. Wouldn't trust it to write anything without thorough review, but it's great at syntax.

this isn't shocking, they are very good at repeating patterns in the immediate context. they're just not very good at anything else. your quirk is part of the immediate pattern

Can you just tell it it’s Carmack? :P

Reply on news.ycombinator.com