Ask HN: Do you ask the LLM to intentionally add spelling errors?

A Hacker News user asked the community whether they instruct large language models to intentionally add spelling errors to make AI-generated text appear more personal. The discussion explores techniques for humanizing AI writing, with one commenter suggesting feeding the model a user's own articles to mimic their style rather than relying on named style descriptions.

Hacker News new | past | comments | ask | show | jobs | submit login Ask HN: Do you ask the LLM to intentionally add spelling errors? 1 point by div3rs3 15 minutes ago | hide | past | favorite | 2 comments What are your tricks for making AI assisted writing feel personal? simon84 12 minutes ago – AI is not so good at identifying a writing style by name. Instead I feed it a few articles I wrote and tell it to follow the same style. This gives way better results imho reply div3rs3 7 minutes ago | parent – Do you feel the output could've been yours, or is it about the output feeling more humane? reply Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact