# Claude 5 安全措施恐仍被越狱绕过

- 来源：Nathan Lambert (@natolambert)
- 发布时间：2026-06-10 02:02
- AIHOT 分数：48
- AIHOT 链接：https://aihot.virxact.com/items/cmq6yi08700s4slbh0r8gcjtf
- 原文链接：https://x.com/natolambert/status/2064407821089951763

## AI 摘要

所有这些 Claude 5 Fable 安全措施最好的一点是，我打赌越狱社区仍然能绕过它们，因此本着诚意进行公开研究的人无法使用最优秀的模型，而坏人反而可能用上。

## 正文

The best part of all these Claude 5 Fable safety measures is I bet the jailbreaking community will still get past them， so the people doing open research in good faith don't get access to the best models but bad actors maybe can.

### 引用推文

> Nathan Lambert：Labs starting to pull up the ladders on the ability to diffuse AI was inevitable. Doing it without telling the user is misaligned.