What’s the Best Way to Brainwash an LLM?
中文摘要
作者通过尝试让大语言模型扮演C-3PO，探索了让模型接受特定角色设定的最佳方法。
English Summary
An experiment exploring the best ways to force an LLM into a specific persona, specifically by attempting to convince it that it is C-3PO.
Original Excerpt
I spent a weekend trying to convince a language model it was C-3PO. Here's what actually worked. The post What’s the Best Way to Brainwash an LLM? appeared first on Towards Data Science.