开源工具Aileaks可扫描代码仓库，揪出泄露的LLM推理轨迹与敏感秘密。
Article URL: https://github.com/sarthakuwar/aileaks Comments URL: https://news.ycombinator.com/item?id=49271711 Points: 3 # Comments: 1
用检查清单测AI对代码仓库架构的理解，RepoProbe带来全新基准。
arXiv:2608.04783v1 Announce Type: cross Abstract: The integration of Large Language Models (LLMs) into software engineering has shifted the focus from…
用开源pipeline，Claude成功找到雅可比猜想反例，AI数学研究新里程碑。
About a month ago, I released under CC0 an implementation of a pipeline I had spent two years developing. It’s the pipeline Claude used to find the co…
最新研究揭示LLM生成代码在真实仓库中的质量与注释模式，为开发者提供实用参考。
arXiv:2607.01867v1 Announce Type: cross Abstract: The use of LLMs in software development has become increasingly widespread on tasks such as code gen…
GitHub正式推出刻录代码仓库到实体光盘的服务，让数字代码存档变成看得见摸得着的物理备份。
IT之家 7 月 3 日消息，微软旗下的代码托管平台 GitHub 今天宣布推出代码仓库刻录 CD-ROM 实体光盘服务。 值得注意的是，GitHub 官方还用一番玩味十足的语气宣发这项服务： 我们听到了大家的声音，并表示认同。 鉴于近期实体媒介的发展，GitHub 欣然宣布：你现在可以将自己的公开…
Remogram为AI代理锻造精准事实，摆脱工作流冗余，开源工具提升仓库与代理的卫生效率。
If you've ever pointed an AI coding agent at a pull request and watched it confidently merge based on a stale title, a truncated API response, or pros…
部落隐性知识如何让AI代理在代码仓库中寸步难行，揭秘开发者间口耳相传的“潜规则”。
Every repo has a little tribal knowledge. The command everyone knows not to run. The service that must be started before tests. The environment variab…
可运行的代码仓库不一定可信，尤其在AI辅助开发时代，信任需要更深层次的标准。
A repo can run and still be hard to trust. That sounds strange at first. If the app starts, the build completes, or the tests pass, the repo is workin…
探索LLM智能体能否从历史失败中学习，解决代码仓库环境配置难题——依赖冲突等常见坑点不再束手无策。
arXiv:2605.26186v1 Announce Type: cross Abstract: Functionality-correct repository setup aims to configure execution environments (e.g., dependencies,…
GitHub官方确认遭黑客攻击，约3800个内部代码仓库数据被盗，安全事件升级。
The code hosting giant GitHub said it was investigating a breach, but said there was no evidence of customer data theft.