Anthropic 研究员：造出模型不等于理解模型，可解释性更像生物学
Anthropic 研究员聊了三年扒开 Claude 内部看运行机制的事，居然发现模型会提前规划好几个 token，听完挺刷新认知的。
Anthropic 可解释性研究员 Emmanuel Ameisen 在 Lenny Rachitsky 的播客中分享了他 3 年来解剖 Claude 等模型内部机制的发现。他提出模型是被“培育”出来的，而非被构建的，因此可解释性工作更接近生物学。他谈到模型会提前规划多个 token 的输出，还讨论了拟人化 AI 反而可能是正确的理解方式。节目还涉及 J-space 与模型对齐、AI 安全之间的关联。
Anthropic AI researcher: “A lot of what we do feels so much closer to biology than to engineering.” Your browser does not support the video tag. 🔗 View on Twitter Lenny Rachitsky @lennysan "To make them is not to understand them." Emmanuel Ameisen ( @mlpowered ) has spent the last 3 years doing interpretability research at @AnthropicAI , looking inside LLMs like Claude to figure out what they're actually doing. As he puts it, models are "grown," not built. We discuss: 🔸 His discovery that models plan many tokens ahead 🔸 Why anthropomorphizing AI can actually be the right approach 🔸 What the "J-space" reveals about how models think 🔸 How interpretability connects to AI alignment and safety Listen no youtu.be/JHo-aiePjoM fpkab 🔗 View Quoted Tweet 💬 4 🔄 1 ❤️ 8 👀 3064 📊 5 ⚡
