1
Buddy Visual Tests
合并前自动审查每个UI变动，让视觉回归测试融入开发流程，省心又可靠。
Every UI change, reviewed before merge Discussion | Link
2
Show HN: LayoutLens: AI-Powered Visual UI Testing
用AI自动检测UI视觉问题，省去手动比对截图，前端测试效率利器！
Article URL: https://github.com/gojiplus/layoutlens Comments URL: https://news.ycombinator.com/item?id=49405683 Points: 2 # Comments: 0
3
In-Situ Behavioral Evaluation for LLM Fairness, Not Standardized-Test Scores
打破AI公平性评测的“应试教育”，用真实行为模式替代标准化测试分数。
arXiv:2605.12530v2 Announce Type: replace-cross Abstract: LLM fairness should be evaluated through in-situ behavioral pattern rather than standardized…
4
The API promised industry keywords. Modern sites kept returning [].
Postman 帮你优雅测试API，一键校验响应结构与Schema，避免数据解析错位问题，调试效率拉满。
This is a submission for DEV's Summer Bug Smash: Smash Stories powered by Sentry . The quietest kind of production bug The endpoint was healthy. Payme…
5
曹操出行正式开放Robotaxi无人化测试
曹操出行正式开放Robotaxi无人化测试，迈入自动驾驶出行新阶段。
36氪获悉，7月27日，曹操出行宣布正式开放Robotaxi主驾无人测试。本次测试在杭州市滨江区的真实城市道路环境开展，以特定站点触发派单的运营机制，在确保安全的基础上，小规模、可控地验证无人化运营的稳定性与服务可靠性。测试车辆已全面接入“曹操智行RAS远程安全服务平台”。
6
From Bug Found to Bug Filed: A Bug-Reporter Skill for Claude Code
Claude Code新增技能：自动将测试失败转化为带证据的bug报告，让复现步骤不再靠猜。
Part 8 of the "Automating Playwright with Claude Code" series. Our pack from Part 6 catches problems (flaky tests, locator issues); this post adds a S…
7
Case study: solving P-99 with LPTP and an LLM
用Claude大模型自动求解经典Prolog问题集，展示LLM在编程任务中的实际能力
arXiv:2607.21196v1 Announce Type: cross Abstract: Ninety-Nine Prolog Problems (P-99) is a famous set of Prolog exercises. We solved the first thirty t…
8
Why Your Unit Tests Aren't Enough (And How to Break Your Own API)
Schemathesis 自动生成 API 测试用例，精准发现单元测试遗漏的 4xx/5xx 错误，并直接集成 FastAPI 等框架
Stop testing the happy path. Learn how to use property-based testing and Schemathesis to automate chaos and break your API before your users do The Pr…
9
I Had 11 AI Subagents Test Every PPTX Skill for Claude Code. Here's What Works
用11个AI子代理实测Claude Code的PPTX生成能力，筛选出真正有效的技巧。
Article URL: https://www.bulaev.net/p/i-had-11-ai-subagents-test-every Comments URL: https://news.ycombinator.com/item?id=49008916 Points: 2 # Comment…
10
The crash that wasn't: debugging CI with AI
用AI找出CI误报崩溃根因，巧妙绕过不可本地复现的难题
Article URL: https://abbyssoul.github.io/engineering/2026/07/19/the-crash-that-wasnt-debugging-kinjo-ci-with-ai.html Comments URL: https://news.ycombi…
11
Show HN: Sentinel – open-source QA agent that reads your code before it clicks
一个能先读懂代码再自动点击测试的开源QA助手，让自动化测试更智能高效。
Hey guys, we built something interesting that we're using for testing / QA with our own products and it's proving to be quite helpful. MIT License - h…
12
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
小鹏第二代VLA在欧洲完成本地化测试，目标成为首家将高阶智驾带入欧洲的中国企业，智能化新突破。
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…
13
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,…
14
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…
15
"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…
16
AnyPoC: Universal Proof-of-Concept Test Generation for Scalable LLM-Based Bug Detection
别再手动验证候选bug了！AnyPoC自动生成可执行测试用例，让LLM漏洞检测从"疑似"走向"实锤"，大幅提升自动化检测的可落地性。
arXiv:2604.11950v2 Announce Type: replace-cross Abstract: While recent LLM-based agents can identify many candidate bugs in source code, their reports…
17
API Testing Strategies: A Practical Guide for Reliable APIs
API测试神器，自动化验证接口响应与性能，多环境管理，让API测试高效可靠。
Most API bugs are not exotic: a missing field, a wrong status code, a timeout under load, or a breaking contract that shipped because nobody verified …
18
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…
19
llm-coding-agent 0.1a0
Simon Willison 的 LLM 编程代理新作，一行代码即可驱动 GPT-5.5 自动修复测试失败，AI 写代码的实用方式再进一步。
Release: llm-coding-agent 0.1a0 Another Fable 5 experiment. Now that my LLM library has evolved into more of an agent framework it's time to see what …
20
Show HN: Bytesalt – AI that finds bugs Playwright tests miss
AI测试新工具，专找Playwright遗漏的bug，覆盖功能、安全、跨浏览器等全面测试场景。
Hey! I built Bytesalt and excited to share it here. Every engineering team I've been part of has had the same problem. Playwright (or similar) scripts…