Pretty cool and shows a clear issue I’ve seen across any LLM. the language and g... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		nfRfqX5n 7 months ago \| parent \| context \| favorite \| on: Brood War Korean Translations Pretty cool and shows a clear issue I’ve seen across any LLM. the language and grammar is so formal/robotic

int_19h 7 months ago [–]

This depends a lot on how the model was fine-tuned. There are many LLaMA tunes that are not at all formal, for example.

With ChatGPT specifically, some forceful prompting can make it sound much better.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact