Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Grok Code Fast 1. Parent comment
Within the boundaries of pre-training, yes. It is definitely possible, in training and in fine-tuning, to make a LLM resistant to engaging in the role-playing requested in the prompt.
There are no comments on this comment yet.
Within the boundaries of pre-training, yes. It is definitely possible, in training and in fine-tuning, to make a LLM resistant to engaging in the role-playing requested in the prompt.