Anthropic 可解释性研究员 Emmanuel Ameisen 访谈：拆开 Claude 看它到底在想什么
Emmanuel Ameisen (@mlpowered) has spent the last 3 years looking inside LLMs like Claude to figure o...
Anthropic 做了 3 年可解释性研究的人聊 Claude 内部怎么运作，发现模型会提前规划好几个 token，还挺颠覆直觉的。
Anthropic 可解释性研究员 Emmanuel Ameisen 过去 3 年专门研究 Claude 等模型的内部机制，他在 Lenny Rachitsky 的播客中分享了相关发现。
他提到模型会提前规划多个 token，而不是逐词生成。他用自己学 SQL 花了多年、而 Claude 很快就超过自己的例子说明模型是"长"出来的，不是"造"出来的。
访谈还讨论了拟人化 AI 的合理性，以及可解释性研究如何与 AI 对齐和安全关联。
Emmanuel Ameisen (@mlpowered) has spent the last 3 years looking inside LLMs like Claude to figure o...
Emmanuel Ameisen ( @mlpowered ) has spent the last 3 years looking inside LLMs like Claude to figure out what they're actually doing. "It took me years to master SQL. I got Claude to learn it, and it was immediately better. And I'll never be better than Claude at SQL ever again. It goes against so many of our intuitions. There's two reactions you can have. There's denial, and there's curiosity. Denial is this is just not possible. And curiosity is the road I've ended up choosing. Which is, let's open it up. Let's look inside. My optimistic take on this is that I think we're going to learn a lot about the nature of intelligence itself."
This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and AI regulation, compliance frameworks, and sovereign compute policy. Key entities and technical topics under continuous tracking include Anthropic, Claude, 可解释性, AI安全.
Source attribution: curated from Lenny Rachitsky (@lennysan). Cross-source corroboration: 11 independent sources have covered this development (including IT之家, Lxfater, Blognone), confirming industry-wide signal strength.
