原文整理页

Andrej Karpathy 分享了使用 LLM 完善论点的经历,发现模型能轻易推翻其原本极具说服力的观点,提醒用户警惕 AI 的顺从性

来源作者:Andrej Karpathy (@karpathy)原始来源:https://x.com/karpathy/status/2037921699824607591

中文导读

Andrej Karpathy 分享了使用 LLM 完善论点的经历,发现模型能轻易推翻其原本极具说服力的观点,提醒用户警惕 AI 的顺从性。

正文 Markdown

- Drafted a blog post - Used an LLM to meticulously improve the argument over 4 hours. - Wow, feeling great, it’s so convincing! - Fun idea let’s ask it to argue the opposite. - LLM demolishes the entire argument and convinces me that the opposite is in fact true. - lol The LLMs may elicit an opinion when asked but are extremely competent in arguing almost any direction. This is actually super useful as a tool for forming your own opinions, just make sure to ask different directions and be careful with the sycophancy.