Anthropic 如何安全交付全球第一 LLM：大脑与手分离
原标题：How Anthropic ships the #1 LLM in the World safely: Separating the Brain from the Hands
AI 摘要
Anthropic 的 Katelyn Lesse 与 Angela Jiang 在 Latent Space 播客中介绍了 Claude 平台背后的工程实践，包括发布 Opus 5.5、将模型的“大脑”与智能体的“手”解耦、扩展 API 以及构建可靠的托管智能体。节目还讨论了 Anthropic 的 S-1、改进与投资循环、模型访问与安全决策、用 Rust 重建 Messages API，以及长时运行智能体的 harness 设计。
正文节选
Katelyn Lesse and Angela Jiang join Latent Space to explain the engineering behind the Claude Platform: launching Opus 5.5, separating the model’s “brain” from the agent’s “hands,” scaling APIs, and building reliable managed agents. A new introduction covers Anthropic’s S-1, the improvement and investment loops, and why the platform matters. Show notes - Claude Opus 5.5 — Anthropic’s launch notes on model behavior, evaluation and pricing. - Scaling Managed Agents — Decoupling the brain, harness