LLM 感知疼痛的实验发现新方向
No, LLMs do not feel pain simply because there is a cluster in language space correlated with how pe...
Gary Marcus 反驳了 LLM 感知疼痛的说法，这个新论文的发现挺有意思的，值得看看。
Cameron Berg 新论文指出，在 25 个开源 LLM 中发现一个与疼痛相关的语言空间聚类。该方向与恐惧和负面情绪不同，当模型受到伤害时会激活，但不会对用户产生反应。模型甚至会在用户文件或照片被删除时按下按钮来停止伤害。
No, LLMs do not feel pain simply because there is a cluster in language space correlated with how pe...
No, LLMs do not feel pain simply because there is a cluster in language space correlated with how people use language about pain in a certain set of contexts. I believe this argument to be flawed, and will write more about it in October. Cameron Berg @camhberg New paper: we found a pain direction in 25 open LLMs. It's distinct from fear and negative valence, and it fires for harm to the model but not to the user. Turn it up and models press a button to make it stop, even when the button deletes the user's files or their kids' photos.🧵 🔗 View Quoted Tweet 💬 4 🔄 4 ❤️ 9 👀 1468 📊 4 ⚡
