Linux内核社区为staging驱动制定LLM使用政策，AI生成代码将面临怎样的审核门槛？一探内核开发治理新动向。
Article URL: https://lore.kernel.org/all/2026080354-skater-urgent-31b2@gregkh/ Comments URL: https://news.ycombinator.com/item?id=49156513 Points: 1 #…
字节+清华姚班背景，这家AI公司一年三轮融资，解决企业级软件工程“提效难”的痛点，不是吹“10倍”，而是Agent Infra与Harness框架带来的真实60%整体提效。
要做硬核的事情，而非摘低垂的果实
大模型生成代码安全研究新基准，揭示领域提示引发的漏洞风险变化
arXiv:2607.25225v1 Announce Type: cross Abstract: LLMs are increasingly used for code generation in critical infrastructure, yet the security effect o…
AI代码泛滥质量堪忧，代码审查流程急需升级——HN社区热议技术生态隐忧
Now that writing code is largely automated, I've seen Github being filled to the brims with slop, and it feels like the overall quality of everything …
2026年 Zig vs Rust 选择再起争论：AI 代码生成能力成新变量，社区经验告诉你谁更香
I used to know people who switched from Rust to Zig, and swore they would never go back to Rust. I personally tried Zig but I definitely prefered Rust…
AI 驱动的 Java 单元测试生成工具，轻松达到 80%+ 覆盖率，支持 Maven/Gradle。
Article URL: https://github.com/JAIPilot/jaipilot-cli Comments URL: https://news.ycombinator.com/item?id=48979793 Points: 2 # Comments: 0
实时编译器反馈让AI写代码更精准，降低迭代成本
arXiv:2607.13921v1 Announce Type: cross Abstract: Languages with rich static semantics, such as Rust, provide stronger guarantees for AI-generated cod…
AI生成代码越来越多，重复问题频发？DupeHound用确定性方法给AI代码上锁，保障代码库整洁高效！
Article URL: https://www.technology.org/2026/07/03/dupehound-deterministic-guardrails-against-ai-code-duplication/ Comments URL: https://news.ycombina…
110个开源测试用例，专门针对AI代码生成中的API集成漏洞，比如Supabase和Auth0，帮助提升代码质量。
As a claude code power user once context compacts it will start writing slop. Especially when writing code for API integrations. For example Supabase …
AI写代码？别被“100%由AI生成”忽悠了，关键在于有没有人盯着。
Article URL: https://www.tommyjepsen.com/blog/supervised-vs-unsupervised-ai-code Comments URL: https://news.ycombinator.com/item?id=48743411 Points: 1…
GitHub近一半新代码由AI生成，但人类逐行审核比手写还慢，AI代码正成为难以处理的“数据堆”。
Article URL: https://maref.cc/en/blog/vibe-coding-crisis/ Comments URL: https://news.ycombinator.com/item?id=48656807 Points: 3 # Comments: 0
Zig 正式封杀 AI 生成代码，贡献者还得玩「扑克」自证清白？开源圈最硬核的信任实验
Article URL: https://kristoff.it/blog/contributor-poker-and-ai/ Comments URL: https://news.ycombinator.com/item?id=48595826 Points: 2 # Comments: 0
不追求一把梭，LLM辅助编程也能细火慢炖，聊聊从容不迫的高效编码方式。
Article URL: https://01max.io/blog/a-comfortable-slow-boil/ Comments URL: https://news.ycombinator.com/item?id=48595253 Points: 2 # Comments: 0
当AI生成“幻觉代码”语法无误但语义错误，多维精度测试成为关键，重新定义“准确”的真意。
When a non-technical founder asks whether an AI app builder produces "accurate" code, they usually mean one thing: does it run without crashing? That …
AI代码助手，实时理解语境并建议代码行，支持多种语言，加速编程效率。
The deal is supposed to help SpaceX's struggling AI division. The company told IPO investors it sees a $26 trillion addressable market in AI.
AI编程助手，实时提供代码建议，提升代码质量与开发效率，注重推理速度和开源生态
IT之家 6 月 14 日消息，小米公司新媒体高级工程师 @小米_邹師傅 今日再度发文，谈起了自己关于大模型的真心话。 1、过去一年国内大模型最让我兴奋的事，不是谁又刷了榜单， 而是行业开始靠作品说话 —— 开源代码放 GitHub 上让人审、论文挂 arXiv 上让人查、模型丢给开发者让人用，算力…
AI加速代码产出后，代码审查正面临前所未有的挑战——你还能跟上团队的节奏吗？
Given the increased use of AI, my experience is that teammates are moving so fast churning out so many changes that it is nigh impossible to review it…
Codex结合GPT-5.5帮你快速排查难复现问题、跨平台构建，专注产品成果
How engineers at Nextdoor use Codex with GPT-5.5 to investigate hard-to-reproduce issues, build across platforms, and focus on product outcomes.
超越功能正确性，提出对齐人类偏好的代码评估框架SWE-IF，让AI生成的代码通过“感觉”检验
arXiv:2510.07315v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have catalyzed vibe coding, where users leverage LLMs to genera…
AI写代码效率高但质量未必好，真正决定软件优劣的是开发环境与工程实践
Article URL: https://adrianferrera.dev/en/blog/ai-does-not-write-good-code Comments URL: https://news.ycombinator.com/item?id=48444459 Points: 2 # Com…