1
Show HN: Wireshark in a TUI
Wireshark 的三栏界面搬进终端，eBPF 加持，连 tcpdump 搞不定的 raw-IP 隧道都能抓包分析。
Article URL: https://github.com/yeet-src/pktscope Comments URL: https://news.ycombinator.com/item?id=49438446 Points: 2 # Comments: 1
2
24 个调试补丁、18 次内核启动：Linux 之父托瓦兹借助 AI 定位 Intel Xe 黑屏故障
IT之家 8 月 26 日消息，科技媒体 Linuxiac 昨日（8 月 25 日）发布博文，报道称 Linux 创始人林纳斯 · 托瓦兹（ Linus Torvalds ）借助 AI， 通过 24 个调试补丁、18 次内核启动，成功排查 Intel Xe 图形驱动中的内存破坏漏洞。 托…
3
上海首条跨长江地铁线，22 号线（市域崇明线）开启列车调试
IT之家 8 月 26 日消息，据央视新闻今天（26 日）下午报道，作为上海首条跨越长江的轨道交通，22 号线（市域崇明线）正式进入车辆交付、全线同步调试验证的关键阶段。同时，全线接触网一次性送电成功、热滑试验顺利收官，线路已具备列车上线调试条件，为全线联调联试迈出关键一步。 22 号线（市域崇明线…
4
Show HN: Apple Unified Logging for Stdio MCP and LSP
为MCP和LSP调试而生，把stdio上的JSON-RPC通信转为苹果统一日志，排查问题更直观。
Article URL: https://github.com/paaloeye/jsonrpc-stdio-proxy Comments URL: https://news.ycombinator.com/item?id=49433171 Points: 2 # Comments: 1
5
Show HN: Python Debug Terminal for VSCode
在 VSCode 里直接跑 Python 调试终端，省去来回切换，调试效率拉满。
Article URL: https://marketplace.visualstudio.com/items?itemName=ernestofgonzalez.vscode-py-debug-terminal Comments URL: https://news.ycombinator.com/…
6
Loupe: a debug overlay that lives inside your React Native app
调试不再靠猜！把网络、日志、存储、深链全塞进App里的沉浸式调试面板，手机端一步到位
The last bug I chased in a React Native app only showed up on a real device, on cellular, in a TestFlight build. So I plugged the phone in, opened a d…
7
Show HN: Helena – API client with no Electron and no accounts, in Go+Fyne
轻量级API客户端，无Electron无账户，原生Go+Fyne构建，支持多认证协议，即开即用。
Article URL: https://github.com/ideaconnect/helena Comments URL: https://news.ycombinator.com/item?id=49363159 Points: 2 # Comments: 1
8
Show HN: I let an AI agent brick my $2.51 ESP32 on purpose
让AI代理主动搞崩ESP32，却能精准定位传感器ISR栈溢出，支持千款开发板，嵌入式调试神器。
Article URL: https://github.com/GLechevalier/nff-core Comments URL: https://news.ycombinator.com/item?id=49366373 Points: 2 # Comments: 0
9
Show HN: Ollama served my 40k-context model at 4k, silently
别被Ollama悄悄缩短上下文坑了，这个小工具帮你检测真实窗口大小。
Article URL: https://github.com/Bigbonus/ollama-context-window-check Comments URL: https://news.ycombinator.com/item?id=49372235 Points: 1 # Comments:…
10
Evaluating Agentic Code Repair Capabilities in Distributed Systems
分布式系统bug修复遇上AI智能体，DDBench双条件评测揭示其真实能力边界。
arXiv:2608.14863v1 Announce Type: cross Abstract: LLM-based coding agents have advanced rapidly on single-process SWE tasks, with frontier models now …
11
Read Your AI Agent's Mind. OpenSearch Observability for LLM Traces.
想知道AI代理为何答错？用OpenSearch追踪LLM调用全链路，定位问题不再靠猜。
You shipped your AI agent. It answers questions, calls tools, retrieves documents, and mostly does the right thing. Mostly. When it does the wrong thi…
12
Kozuchi Agent: A Language-Agnostic Open-Weight Agent for Software Repair
开源权重、语言无关，Kozuchi Agent 为软件自动修复带来跨语言新范式。
arXiv:2608.15579v1 Announce Type: cross Abstract: Industrial software-engineering teams increasingly need LLM agents that turn bug reports into correc…
13
Rethinking Automated Program Repair: The Impact of Bug Complexity, Fault Localization, and LLM Cost-efficiency
不只是修bug，这篇研究重新审视了缺陷复杂度与定位策略，用成本效率视角重构自动化修复的边界。
arXiv:2608.14065v1 Announce Type: cross Abstract: Background: Software bugs remain a critical challenge in development, necessitating effective Automa…
14
Show HN: Rungraph – See your AI coding-agent runs as a graph
把AI编程代理的每次运行变成可视化图谱，快速定位问题，提升调试效率。
Article URL: https://github.com/fayzan123/rungraph Comments URL: https://news.ycombinator.com/item?id=49321388 Points: 1 # Comments: 0
15
科技行业史上最大收购之一，SpaceX 豪掷 600 亿美元拿下 AI 编程公司 Cursor
一句提示词搞定代码生成与调试，AI驱动的编程助手正重塑开发流程
IT之家 8 月 14 日消息，SpaceX 完成了对 AI 编程初创公司 Cursor 的 600 亿美元 （IT之家注：现汇率约合 4,054.22 亿元人民币） 收购。 对于马斯克而言，这笔交易是追赶 Anthropic 和 OpenAI 的重要一步。监管文件显示，收购于当地时间 8 月 14…
16
LAUDE: LLM-Assisted Unit Test Generation and Debugging of Hardware DEsigns
用大模型自动生成硬件单元测试并辅助调试，直击芯片验证痛点。
arXiv:2601.08856v3 Announce Type: replace-cross Abstract: Unit tests are critical in the hardware design lifecycle to ensure that component design mod…
17
Show HN: Watching browser fingerprinting calls via Chromium's Blink layer
深入 Chromium Blink 层，实时捕捉浏览器指纹调用，精准验证反检测配置，是反爬对抗调试利器。
Article URL: https://kameleo.io/blog/this-is-the-closest-well-ever-get-to-reverse-engineering-anti-bots Comments URL: https://news.ycombinator.com/ite…
18
Ghidra internals: Where are my logs ?
想知道Ghidra日志藏在哪里？这篇内部指南带你快速定位application.log。
Ghidra uses the Apache Log4j logging library to store a lot of execution messages. Finding these logs can be quite tricky, especially if you launch Gh…
19
Debugging a failed agent run costs more than the run itself
AI agent调试失败的成本远超运行本身，揭示故障恢复中隐藏的巨额开销。
Originally published on Loop & Retry — field notes on building LLM agents that survive production. Here is the intuition to kill: a failed run is …
20
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…