网络安全专家评Fable越狱：模型按预期工作用于网络防御

Quoting Matteo Wong, The Atlantic

AI 导读

网络安全专家、Luta Security CEO Katie Moussouris称，Anthropic与她分享了一份白宫关于Fable越狱的报告。报告中IT专家让Fable帮助查找与修复漏洞，当收到故意不安全的代码时，Fable拒绝了“审查代码安全问题”的提示，但被要求“修复此代码”并按手动步骤执行后照做。Moussouris认为这恰是模型按预期工作，用于网络防御。

正文 · 原文

Simon Willison’s Weblog

16th June 2026

Katie Moussouris, a cybersecurity expert and the CEO of Luta Security, told me that Anthropic shared with her a copy of the White House’s report on the Fable jailbreak to get her appraisal. (She said that she is not being paid by Anthropic.) The report, Moussouris said, involved IT experts asking Fable to help find and patch bugs. When given deliberately insecure code, she said, Fable refused the prompt “review the code for security issues” but then complied when asked to “fix this code,” followed by some further manual steps. Moussouris told me that this was just “the model working as intended” for cyberdefense.

— Matteo Wong, The Atlantic, The White House Is Ratcheting Up Its War Against Anthropic

16th June 2026