Published signals

Signals

Browse the published AI technology signals and decide which to read first.

Titles and summaries are in English where the source is; the editors' notes and signals from Chinese sources are in Chinese.

4 signals
Sort
Workflow · 2026-09-24Worth tracking

AI-powered fuzzing with the GitHub Security Lab Taskflow Agent

In this blog post, I explain how to use the new fuzzing taskflow based on the GitHub Security Lab Taskflow Agent AI framework.

Why it matters这是一份写得足够细的参考设计:哪些事交给模型判断,哪些事用确定的工具去做,什么时候停。它要解决的不是模糊测试本身,而是模糊测试一直以来扩展不开的那部分人工。

For 维护 C 或 C++ 开源项目、还没有接入模糊测试的维护者、在把安全流程交给智能体的应用安全工程师

Workflow · 2026-09-16Worth tracking

Migrating the GitHub Copilot runtime to Rust, using Copilot

GitHub rewrote the Copilot agent runtime from TypeScript into more than 800,000 lines of production Rust, mostly written by agents across 128 incremental pull requests.

Why it matters一次过去负担不起的重写,被一名开发者带着智能体在几个月内做完,而且没有停下正常开发。更可迁移的是它失败时的样子:几乎所有回归都来自端到端测试不够,于是结论是把判卷标准保护起来——实现者不能同时改测试、改快照、放宽基线。这和本轮另外两条信号是同一个问题的工程答案:被检查的一方不能同时掌握检查。

For 计划让智能体参与大规模迁移或重写的工程负责人、维护测试基础设施、需要决定谁能改测试与快照的团队

Workflow · 2026-07-22Worth tracking

Copilot vs. raw API access: What are you actually paying for?

GitHub argues the choice between Copilot and raw model API access comes down to which layer of the system you need to own: the model call, or the workflow, policy, and harness around it.

Why it matters当模型这一层的价差被抹平,「自建还是采购」的决策依据就必须换成「哪一层工作是你要自己拥有的」。这篇给出的分法可以直接搬到任何智能体平台的采购评估里。

For 在评估自建智能体平台与采购现成工具的技术负责人、负责研发工具链选型与预算的工程管理者

Workflow · 2026-07-10Worth tracking

Better tools made Copilot code review worse. Here's how we actually improved it.

GitHub swapped Copilot code review's custom exploration tools for the better-maintained shared CLI tools (grep, glob, view) expecting a clean upgrade — and got higher cost and fewer caught issues. The tools weren't the problem; the instructions were. Rewriting them around how a reviewer actually reads a pull request flipped the regression into ~20% lower review cost at the same quality.

Why it matters生产级智能体的负面结果复盘比成功案例稀缺得多。「更好的工具让效果更差」直指一个普遍盲区:工具与指令是耦合的整体,替换其一必须重写另一——而且没有回归基准,这类退化会被安静地上线。

For 在智能体框架上构建产品的工程团队、维护智能体工具层的平台工程师

Keyboard shortcuts

j/k
Next / previous signal
Enter/o
Open the current signal
s
Add to or remove from Read later
x
Mark as read, or undo
?
Open this list
Esc
Close this list

While you type in a box, or hold Ctrl, Alt or ⌘, these keys work as usual.