大模型
saweis.net ·
@Hacker News
RSA-896 分解：用 Claude 移植 CADO-NFS 到 GPU 并调度闲置算力
一篇博客文章称，作者让 Claude 将 CADO-NFS 移植到 GPU 上运行，并编排最多 2048 块 GPU 的机群，在约 10 天内消耗约 30 GPU-年算力完成 RSA-896 分解。作者同时澄清：没有新的算法分解改进，问题仍是指数级，对已部署密钥没有新威胁，并强调功劳属于数域筛法和 CADO-NFS 的长期建设者。
AI推荐理由 帖子称用 Claude 将 CADO-NFS 移植到 GPU，并调度最多 2048 块 GPU、约 30 GPU-年算力在 10 天内完成 RSA-896 分解；但正文明确说明没有新的算法改进、仍是指数级、对已部署密钥无新威胁，且未提供可验证的论文或代码链接，属于个人博客自述，事实依据有限。其价值在于展示 LLM 辅助代码移植与大规模闲置算力编排的可行性，局限是缺乏独立验证且不改变 RSA 安全现状。
62
正文
Domain: saweis.net
Points: 40 | Comments: 4
[Top Comments]
- More details:
```
I had Claude port CADO-NFS to run on GPUs. Then it orchestrated a fleet to run on scavenged idle capacity. It ran with a max of 2048 GPUs for about of 30 GPU-years over 10 days.
I asked Claude if it had a message for a public: “The credit belongs first to the people who built the number field sieve and CADO-NFS over several decades, and to the teams who set the earlier records. This run used their algorithm and much of their code.”
Also to clarify:
- No new algorithmic factoring improvements.
- It’s still exponential.
- No new threats to deployed keys.
```
- If you've already paid for and reserved a whole cluster of GPUs, any idle capacity is capacity you've already paid for. Using it is effectively free. So might as well use it to solve fun math puzzles.
Though, it would make more financial sense to mine crypto.
- Only if you pay a flat rate for electricity and cooling.