1
小鹏第二代 VLA 完成欧洲本地化测试，何小鹏期望成为首家将高阶智能辅助驾驶带到欧洲的中国企业
IT之家 7 月 15 日消息，小鹏汽车副总裁 @托马斯电火车 今日透露，7 月 14 日，小鹏集团董事长、CEO 何小鹏在德国完成小鹏图灵 AI 智驾（NGP）第二代 VLA 模型的本地化验收测试。 他表示，这套基于中国路况训练的智能辅助驾驶系统在欧洲的适配性和稳定性已经很高， 几乎不需要额外数据…
2
Agent Hacks Agent: Autoresearch for Production-Agent Red-Teaming
让AI Agent自动互相攻击，发现生产环境漏洞，这篇论文提出了全新的自动化红队测试框架。
arXiv:2607.11698v1 Announce Type: cross Abstract: Production LLM agents such as Claude Code and Codex operate over untrusted content, files, commands,…
3
Testing LLMs Like Software: A Promptfoo Deep Dive for QA Engineers
深入探索Promptfoo工具，让QA工程师像测试传统软件一样高效测试LLM，附赠完整手册。
Want the full 46-page handbook? Promptfoo for QA: The Complete Engineer's Handbook (2026 Edition) by Himanshu Agarwal covers everything below in produ…
4
"The price table most AI cost tools multiply by has one automated test: jq empty
AI成本工具定价表仅依赖一个jq测试，历史价格被覆盖导致费用计算错误，点明数据管理隐患。
Most tools that tell you what your AI usage costs work the same way: count tokens locally, multiply by a shared price table. For most of the ecosystem…
5
米哈游精灵养成游戏《崩坏：因缘精灵》「进化测试」内容前瞻发布，7 月 9 日开测
IT之家 7 月 6 日消息，米哈游旗下精灵养成游戏 ——《崩坏：因缘精灵》「进化测试」已官宣定档 7 月 9 日，招募时间为 2026 年 6 月 22 日 12:00 - 2026 年 7 月 3 日 23:59。 IT之家注意到，米哈游官方今日放出了此次「进化测试」的内容前瞻。据介绍， 玩家在…
6
Show HN: Ocarina – Automate and test MCP servers from YAML, no LLM
用YAML脚本自动化测试MCP服务器，无需LLM参与，支持确定性回放和场景验证。
Hi all. As someone who has spent years working with Ansible and other automation frameworks, the recent MCP boom has me fascinated. People are creatin…
7
米哈游《崩坏：因缘精灵》进化测试定档 7 月 9 日，现已开启报名
IT之家 6 月 22 日消息，米哈游《崩坏：因缘精灵》今日官宣「进化测试」定档 7 月 9 日，官方 PV 及实机演示同步放出，招募时间为 2026 年 6 月 22 日 12:00 - 2026 年 7 月 3 日 23:59。 据官方介绍，用户可以在浏览器里搜索《崩坏：因缘精灵》进入主页，登录…
8
MORTAR: Multi-turn Metamorphic Testing for LLM-based Dialogue Systems
提出MORTAR框架，用蜕变测试自动化生成多轮对话用例，精准检测LLM对话系统的不一致行为。
arXiv:2412.15557v4 Announce Type: replace-cross Abstract: With the widespread application of LLM-based dialogue systems in daily life, quality assuran…
9
ProbeLLM: Automating Principled Diagnosis of LLM Failures
自动化诊断大模型失败原因的新框架，用原理性方法定位LLM错误根源。
arXiv:2602.12966v2 Announce Type: replace Abstract: Understanding how and why large language models (LLMs) fail is becoming a central challenge as mod…
10
Ask HN: What do you use for throwaway email inboxes in CI pipelines?
HN社区热议CI管道中用于测试的临时邮箱方案，Mailhog、Mailtrap等工具优劣势对比
Testing auth flows (password resets, magic links, email verification) always requires a real inbox. Curious what the HN crowd is actually using. Mailh…
11
Automated QA and Testing with AI
AI如何颠覆软件测试？揭秘自动化测试新纪元。
Article URL: https://antirez.com/news/168 Comments URL: https://news.ycombinator.com/item?id=48433351 Points: 9 # Comments: 3
12
New version of "peers" – the AI couple doing things
零缺陷不是吹的！AI结对编程工具peers新版上线，50000随机测试无bug。
Article URL: https://github.com/c0decave/peers Comments URL: https://news.ycombinator.com/item?id=48422239 Points: 1 # Comments: 0
13
Smack – AI personas that run UX tests on any URL local
用AI模拟不同用户角色，在本地URL上自动跑UX测试，省时又高效
Article URL: https://smck.ai/ Comments URL: https://news.ycombinator.com/item?id=48425088 Points: 2 # Comments: 0
14
PerceptUI: LLM Agents as Human-Aligned Synthetic Users for UI/UX Evaluation
用LLM模拟真实用户评估UI/UX，自动生成人类对齐反馈，大幅降低人工测试成本。
arXiv:2606.05697v1 Announce Type: new Abstract: User interface (UI) and user experience (UX) evaluation is central to product development, yet reliabl…
15
AI based Software Testing system that works
主打真实可用的AI软件测试系统，一键自动化测试，提升开发效率。
Article URL: https://ytest.ai/ Comments URL: https://news.ycombinator.com/item?id=48360242 Points: 3 # Comments: 0
16
QAOnFire – AI generates manual test cases on every PR
每份PR自动生成手动测试用例，安全轻量不泄露源码，免费每月5次
Article URL: https://qaonfire.dev Comments URL: https://news.ycombinator.com/item?id=48366770 Points: 1 # Comments: 0
17
Show HN: HtmlUnit 5.0.0 Is Available
Java程序的「无头浏览器」，支持自动化测试与网页抓取，即将添加HTTP/2支持，开源且稳定。
The biggest change: JDK 17 is now the minimum required version. Other highlights: JavaScript Engine got major improvements (e.g. RegExp; Scope handlin…
18
Automated Self-Testing as a Quality Gate: Evidence-Driven Release Management for LLM Applications
用自动化自测作为质量门控，实现LLM应用证据驱动的发布管理，论文提出系统方法与实证数据。
arXiv:2603.15676v2 Announce Type: replace-cross Abstract: LLM applications are AI systems whose nondeterministic outputs and evolving model behavior m…
19
Show HN: Dari-docs – Optimize your docs using parallel coding agents
用并行AI代理自动优化技术文档，让文档质量从“人能看懂”升级到“智障级代理也能完成任务”。
It’s well known at this point that documentation needs to be optimized for AI agents - we’re all pointing our Claude Code / Codex / Pi agents at docum…
20
Addendum to o3 and o4-mini system card: Codex
OpenAI发布Codex系统卡附录，详解专为软件工程优化的o3变体，强化学习驱动自动化编码与测试。
Codex is a cloud-based coding agent. Codex is powered by codex-1, a version of OpenAI o3 optimized for software engineering. codex-1 was trained using…