1
代码显示 Meta 拟拆分移动平台 Horizon App 内置游戏功能，将推出独立应用
IT之家 8 月 31 日消息，消息源 NoridoesVR 在拆解 Meta Horizon 手机 App 时发现，Meta 计划将 Horizon Worlds 游戏功能从相应 App 中拆出。相应项目内部代号为“Eclipse”，命名预计为“Horizon Create”。 参考IT之家先前报…
2
Evaluating Inference-Time Defenses Against Package Hallucination in LLM-Generated Code
大模型写代码常“编造”不存在依赖包？这篇论文系统评估了推理时防御手段，帮你避开代码幻觉坑。
arXiv:2608.22652v1 Announce Type: cross Abstract: LLMs are increasingly used for code generation, yet they frequently hallucinate non-existent softwar…
3
代码显示苹果 HomeHub 智能家居中枢设备支持识别用户面容，以便实现自动切换不同账号
苹果HomeHub智能家居中枢，面容识别自动切换账号，让全家人都能享受专属智能体验。
IT之家 8 月 25 日消息，据在 macOS Tahoe 26.7 更新中发现的代码，苹果正在开发的智能家居中枢设备 HomeHub 将支持多用户配置文件，能够通过识别用户面容来自动切换不同账号。 从代码信息来看，这款家居中枢能够针对不同家庭成员显示“个人内容（Personal Content）…
4
代码显示谷歌正在为 Google Play 商店应用开发 AI 图片搜索功能
谷歌Play商店将推AI图片搜应用，截图上传即可精准匹配，告别模糊关键词搜索
IT之家 8 月 25 日消息，外媒 Android Authority 在挖掘谷歌 Google Play 商店应用 v52.8.55-34 版本时发现，谷歌正在为应用内置的 AI 搜索功能 Ask Play 开发图片搜索功能。 目前，Android Authority 已成功在应用中启用了部分相…
5
Vibe Coding on Trial: Operating Characteristics of Unanimous LLM Juries
当单个大模型评代码不够可信，让多个LLM组成「陪审团」一致表决会怎样？实验数据揭示真相
arXiv:2602.18492v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are now good enough at coding that developers can describe inte…
6
Malware that runs the moment you open the project
打开项目瞬间中招？揭秘利用编辑器漏洞的恶意代码手法
"A dropper family committed straight into developer repos. It executes on next dev or when VS Code opens the folder — no npm install needed. How it hi…
7
Do Not Copy/Paste: Soft Barriers for Copying in AI-Assisted Programming
揭秘AI辅助编程中的复制粘贴软屏障，为开发者提供防误操作的协作新思路
arXiv:2608.22638v1 Announce Type: cross Abstract: Copying a function from a chat window into an editor takes less than a second. For many uses of AI c…
8
Repo2Skill-Evo: Repository Skills Go Stale in Silence
代码仓库技能悄悄过时，Repo2Skill-Evo如何让AI编程技能永葆新鲜？
arXiv:2608.21964v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly operate over evolving software repositories, where succ…
9
AI-to-AI Code Reviews of GitHub Pull Requests
AI 自动审查 GitHub 拉取请求，实证研究揭示效果与挑战
Article URL: https://arxiv.org/abs/2608.21311 Comments URL: https://news.ycombinator.com/item?id=49426227 Points: 1 # Comments: 0
10
Scaling Memory Safety: AI-Assisted Rewrites of C/C++ Dependencies to Rust
AI辅助将C/C++依赖重写为Rust，谷歌揭示规模化提升内存安全的实战路径。
Article URL: https://bughunters.google.com/blog/scaling-memory-safety Comments URL: https://news.ycombinator.com/item?id=49422826 Points: 6 # Comments…
11
GitHub Copilot After 10 Months: Reliable Autocomplete, and a Security Story Our Review Doesn't Cover Yet
10个月实测GitHub Copilot：自动补全可靠，但安全隐忧值得警惕，附最新定价分析。
We've kept GitHub Copilot installed for close to a year. It's no longer the tool we reach for first on hard problems, but it's the one we fall back on…
12
Architecture as Capability Equalizer for Coding Agents
揭秘架构如何成为编码智能体的能力均衡器，为提升代码生成质量提供新视角。
arXiv:2608.21747v1 Announce Type: cross Abstract: LLM-based coding agents generate complete software systems from high-level descriptions, yet little …
13
Show HN: RepoRoulette: Randomly Sample Repositories from GitHub
随机抽样GitHub仓库，帮你发现隐藏的优质开源项目，探索未知代码宝库。
Article URL: https://github.com/gojiplus/reporoulette Comments URL: https://news.ycombinator.com/item?id=49424079 Points: 2 # Comments: 0
14
Concepts for Securing Agentic AI Coding and the Terok Environment
AI编程助手的安全短板怎么补？这篇论文用Terok环境给出了可落地的防护思路。
arXiv:2608.22930v1 Announce Type: new Abstract: Agentic AI is a fascinating new tool for software development. It is a huge step forward compared to "…
15
How to Quickly Understand and Improve AI Agent Design
从系统设计视角拆解AI Agent构建，借Bob大叔观点快速提升设计敏感度，直击编码Agent的软肋。
Coding with agents really has surfaced a bunch of problems and challenges we never ran into when writing code by hand. Agents work even faster than yo…
16
Temporal Validity on Real Software Histories: Eliminating Stale-Fact Errors in Code-Assistant Memory over GitHub Fixes
代码助手RAG分不清新旧事实？这篇研究用真实软件历史消除陈旧事实错误，直击AI记忆的时间盲区。
arXiv:2608.20685v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) has no model of time: when a fact changes across a coding sessi…
17
I Shouldn't Need an LLM to Explain My LLM
揭秘AI圈“自我舔舐”陷阱：用LLM解释LLM，代码生成的测试金标准还能可信吗？
Article URL: https://daviesgeek.com/I-Shouldn%E2%80%99t-Need-an-LLM-to-Explain-My-LLM Comments URL: https://news.ycombinator.com/item?id=49409282 Poin…
18
微软 Windows IKE 严重漏洞确认已遭恶意利用：攻击者无需认证即可远程执行代码
微软 Windows IKE 服务曝严重漏洞，攻击者无需认证即可远程执行代码，已被实际利用，请尽快修复。
IT之家 8 月 22 日消息，美国网络安全和基础设施安全局（CISA）于 8 月 18 日将 Windows Internet Key Exchange（IKE）服务扩展组件中的一个严重远程代码执行漏洞纳入其已知被利用漏洞目录（KEV），并确认该漏洞已被积极利用。 该漏洞编号为 CVE-2026-…
19
Show HN: Structural code grep across public GitHub repositories
用AST模式语法跨GitHub海量仓库做结构化代码搜索，找模式快人一步。
Codemod grep searches public code by syntax and structure, not just text or regex. Use ast-grep patterns to find code by shape across repositories. Co…
20
AI Engineering for Web Developers: From Vibe Coding to Production
告别“聊天式”写代码，看Web开发者如何把AI从玩具变成生产工具
The End of 'Vibe Coding' For the past year, the industry has been enamored with 'vibe coding'—the act of throwing natural language prompts at an LLM a…