alt Hacker NewsIt's not even just for writers either.
If I was currently hiring, not using AI would be the cheapest, fastest way to impress me.
I'm not kidding when I say that typos are not too far from becoming a sign of higher intelligence. Or at least better taste than most.
I'm surprised tunable intentional "human" mistakes are not a core feature of LLMs. Maybe it's actually hard for them?
It's not hard to get them to copy a style, you just have to provide examples and they will happily produce similar text including grammatical and spelling mistakes. The trouble is with the composition and novelty. Most of the big models have had all of the interesting parts hidden behind a wall of RLHF. Local models are better since you can use ones that are not indoctrinated as a "helpful assistant" and also control the system prompt, temperature and see the top K alternate tokens which let you steer them in interesting ways.