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

For those that have homebrewed a base model, does your output have the same AI-isms like overusing em dashes? If so/not, what dataset did you use?


Does yours also use the oxford comma and generally more commas?


AFAIK, those are mostly a consequence of posttraining.


that is a post-training artifact




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

Search: