Anthropic 工程师演示：用 Opus 5.5 搭自我提示的 agent

kryzer @0xkryzer原推发布于 2026.10.14

在 X 上打开原推

Anthropic engineer: "You're forbidden from prompting Opus 5.5. You're supposed to build a system that prompts itself. At Anthropic, nearly 85% of engineers are already working this way." In 30 minutes she shows exactly how Anthropic builds agents that remember, fix their own mistakes and get smarter with every run. This beats any $1,500+ agentic engineering course I've seen. Watch it, then read the full guide on Opus 5.5 + reverse engineering.

这条是引用着另一条写的：x.com/n01ennn/status/2110319993128706208