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.”
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 Anthropic: Research, IT之家, Lxfater), confirming industry-wide signal strength.
