Hacker News · 首页· eatitraw·· 2026-10-04AI 评分20
我们的 AI 助产士：用 ChatGPT 扮演角色回答医疗问题的实验
Our AI Midwife
AI 导读
作者用 ChatGPT 扮演不同角色来回答医疗问题，发现角色台词少或词汇有限时，模型会脱离角色设定直接作答。Furby 很快就"跑偏"，星际争霸2 的 Abathur 几句之后也开始像普通 LLM 一样说话。
正文
> Strangely, there were many times where ChatGPT decided it would answer our medical question, but not in the form of a TV medical script. The tides had completely turned!
I've noticed this happens a lot with characters that don't have any long lines and/or have limited vocabulary.
Furby trails off pretty quickly, Abathur from StarCraft 2 (great for shortening code comments BTW) starts talking like a typical LLM after a few sentences.
来源：Hacker News · 首页 · news.ycombinator.com