📰 2026-05-08 03:00 更新
🔸 Natural Language Autoencoders: Turning Claude’s Thoughts into Text / 自然语言自动编码器：将克劳德的思想转化为文本
🔗 Natural Language Autoencoders: Turning Claude’s Thoughts into Text
🔥 27 points
原文:
When you talk to an AI model like Claude, you talk to it in words. Internally, Claude processes those words as long lists of numbers, before again producing words as its output. These numbers in the middle are called activations—and like neural activity in the human brain, they encode Claude’s thoughts.Also like neural activity, activations are difficult to understand. We can’t easily decode them to read Claude’s thoughts. Over the past few years, we’ve developed a range of tools (like sparse…
译文:
当您与Claude这样的人工智能模型交谈时，您会用语言与之交谈。在内部， Claude将这些单词作为一长串数字进行处理，然后再次产生单词作为其输出。中间的这些数字被称为激活，就像人脑中的神经活动一样，它们编码克劳德的思想。与神经活动一样，激活也很难理解。我们无法轻易解码它们以阅读克劳德的想法。过去几年 ，我们开发了一系列工具（如稀疏…
自动更新 · 正文抓取 · 双语翻译