4 posts tagged with "Open Source"

If you've worked with an AI coding agent, you've seen this scene: the agent finishes a task and reports, full of confidence — "All tests pass ✅". You open the page. Blank screen. Or the API returns 404. "Pass," it turns out, sometimes just means the agent believes it passed.

This is the awkward spot AI-assisted development is in: writing code is no longer the bottleneck — acceptance is. Without watching every change and clicking through every feature yourself, how do you know what the AI delivered actually works, end to end? I made the broader case in The Last Mile of AI Is Infrastructure, Not Intelligence: the intelligence is already good enough; what's missing is exactly this kind of infrastructure.

The two common answers both fall short. Manual acceptance after every change can't keep up with an agent's output — and human eyes miss exactly the worst failures, the ones where the system claims it's fine while a critical path is quietly broken. End-to-end (e2e) tests are, in practice, a program you maintain forever: async, waits, retries, flakiness — and an agent refactoring the internals breaks them constantly. Worse, these days the tests are often AI-written too. When the player is also the referee, a green light doesn't carry much weight.

We built Duhem — an open-source holistic verification tool — because we think there's a third way. This post covers what it is, and a real bug it recently caught in our own product: one that fooled even the container's built-in health check, and that Duhem stopped before release.

Six protocols. Six automation levels. Seventeen tools. Twelve predictions. One interactive map that ties them all together.

The AI Agent Interaction Landscape is an open-source, bilingual SPA I built to make sense of how AI agents interact with developers, editors, tools, and each other in 2026. This article walks through the key frameworks it introduces—and the insights that emerged from building it.

Earlier this year, I was amazed by agentic AI coding with Claude Sonnet 3.7. The term "vibe coding" hadn't been coined yet, but that's exactly what I was doing—letting AI generate code while I steered the conversation. It felt magical. Until it didn't.

After a few weeks, I noticed patterns: code redundancy creeping in, intentions drifting from my original vision, and increasing rework as the AI forgot context between sessions. The honeymoon was over. I needed structure, but not the heavyweight processes that would kill the speed I'd gained.

Background​

Many excellent programmers and technical professionals enjoy writing technical articles and blogs as a way to share and spread knowledge and experience, expand their visibility and influence, attract followers, and some tech bloggers even earn advertising revenue through writing. Many excellent bloggers have also gained opportunities to publish books and find jobs through this method. Therefore, writing technical articles is a very worthwhile investment that helps oneself while benefiting the public.

However, writing technical articles is usually time-consuming, especially for high-quality articles. Not only do they require extensive research, thoughtful article structure, and consideration of the target audience, but they also require a lot of preliminary work, such as setting up environments, writing demo code, testing code, and so on. A high-quality technical article typically takes 3-6 hours to complete. However, spending a lot of time writing articles only to have them receive little attention upon publication is quite frustrating. We believe that quality articles deserve attention and dissemination, allowing more technical workers to gain knowledge and benefit from reading them.

Every tech blogger has their preferred technical media platforms, such as Juejin, CSDN, WeChat Official Accounts, etc. Many tech bloggers also like to publish articles on different platforms to seek maximum attention while preventing their hard work from being copied and plagiarized by others. However, publishing on multiple platforms is troublesome: bloggers need to log into multiple media platforms simultaneously and copy-paste their articles one by one. What's more troublesome is that some platforms only support Markdown while others only support rich text, requiring bloggers to convert between the two, which increases workload.

The multi-platform publishing tool ArtiPub solves exactly this problem. Below, we'll introduce the recently launched open-source multi-platform publishing platform ArtiPub.