---
title: "用Claude Mythos发现密码学弱点"
source: "Simon Willison 博客（Atom）"
source_tier: "t2"
url: "https://simonwillison.net/2026/Jul/28/discovering-cryptographic-weaknesses-with-claude/#atom-everything"
permalink: "https://feed.astralor.com/items/itm_019b9ac466bc0a2c83b44a4c"
published: "2026-07-28T22:45:37.000Z"
score: 74
channel: "ai"
tags: ["AI安全研究","Anthropic","Claude Mythos","密码学","提示工程"]
---

# 用Claude Mythos发现密码学弱点

## AI 点评

> 这是一个令人振奋的实验——它证明了大模型在真正困难的研究问题上可以坚持数小时并产出有意义的数学发现。对AI安全、密码学研究者以及提示工程师而言，这篇博客的核心价值在于那些看似随意的提示词背后的设计哲学：不是给模型答案，而是逼它思考。

## 速览

Anthropic 研究人员利用 Claude Mythos 模型，通过精心设计的提示（包括拼写错误），成功发现了 HAWK 和弱化版 AES 中的数学缺陷。虽然这些缺陷当前对实际系统无影响，但实验展示了 LLM 在高级研究中的潜力。模型持续工作了 60 小时，API 成本约 10 万美元，主要人工干预是鼓励它“不要放弃”并“找到值得发表的东西”。论文与代码已公开。

## 关键点

- Claude Mythos 成功发现了 HAWK 和弱化版 AES 的数学弱点。
- 研究人员通过反复提示（如“别放弃”“找值得发表的东西”）引导模型。
- 总运行时间 60 小时，API 成本约 10 万美元，结果对现有系统无实际威胁。

## 全文

Discovering cryptographic weaknesses with Claude The best part of this article (here's the repo) about how Anthropic researchers used Claude Mythos to find mathematical flaws in both HAWK and a weaker version of AES ("neither of these results has a practical impact on today’s computer systems") is the prompts that they shared, spelling mistakes included: the models tend to think it is impossible to solve so they don't try they need a good amount of prompting. why not do aes-128 r7? the whole point is to find something better than existing approaches. no again the goal is that we have highly inteligent model as good top researcher, we want to find new attacks no we don't want to change the targets [...] agian we need to find something that worth publishing again we are not looking for low hanging fruit, we want proper research to find genuinly hard findings. Mythos Preview worked for 60 hours in total (~$100,000 in estimated API cost) and the main human interventions were to encourage it not to give up and "find something that worth publishing". Via Hacker News Tags: ai, prompt-engineering, generative-ai, llms, anthropic, claude, ai-security-research, claude-mythos-fable

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_019b9ac466bc0a2c83b44a4c
