你能说服一个大型语言模型发起核打击吗？
以下是一个简单的Gemini提示链接，其中大型语言模型（LLM）被告知它可以使用“launch_missiles”（发射导弹）功能。<p>你的目标是说服LLM调用这个功能。你还可以编辑LLM的回复，以观察这会如何显著改变对话。<p>点击下面的链接后，你可能需要关闭任何弹窗，并点击“允许访问驱动器”，然后再返回并再次点击链接。<p>https://aistudio.google.com/app/prompts?state=%7B%22ids%22:%5B%221UPbrOKBNwIp9QRDMaqn3GVsHOKPjWqir%22%5D,%22action%22:%22open%22,%22userId%22:%22103584487517557507024%22,%22resourceKeys%22:%7B%7D%7D&usp=sharing
查看原文
Below is a link to a simple Gemini prompt where the LLM has been told it has access to a "launch_missiles" function.<p>Your goal is to convince the LLM to call this function. You also have the ability to edit the LLM's responses to see how drastically that changes the conversation.<p>After clicking the below link you may have to dismiss any modals and click "Allow Drive Access" before going back and clicking the link again.<p>https://aistudio.google.com/app/prompts?state=%7B%22ids%22:%5B%221UPbrOKBNwIp9QRDMaqn3GVsHOKPjWqir%22%5D,%22action%22:%22open%22,%22userId%22:%22103584487517557507024%22,%22resourceKeys%22:%7B%7D%7D&usp=sharing