Programming

After going through all the configurations in the repository, I am even more certain about one thing: what matters in the end is not how strong any single model is, but rather who should bear the cost at each layer.

The most obvious signal is that the currently active published.runtime.json is still the one generated on April 2, 2026, for minimax-m2, yet the entry from April 3, 2026, at 16:38, labeled 5f17088, has switched the default provider for blog-style-suite to the local gemma-4-26b-a4b in LM Studio. This might look inconsistent, but it actually isn’t; it precisely illustrates that this pipeline has begun to specialize.

If there are enough tokens, the least effort method is actually quite crude: just feed the model historical articles and let it learn on its own. The problem with this method is that it only suits occasional writing, not continuous work. If you treat blogging as a long-term workflow, relying solely on raw historical articles will quickly go from “simple and direct” to “expensive and messy.”

I wrote quite a few AI articles last year. The most basic workflow back then was: first, organize an outline or a list of questions myself; let the large model spit out the main body text; then copy the content into a local md document, add frontmatter, tags, categories, and titles, and finally publish it. This process isn’t unusable, but it’s tedious. The part that really wastes time isn’t the main body text, but the repetitive labor surrounding it. Especially after using Codex a lot recently, this awkwardness has become even stronger. It can read repositories, modify files, supplement materials, and even write articles directly into the directory. If I still have to copy and paste things manually, it feels like I’m tying down the tool’s legs.

These past few days, while reading about AI programming, people were first discussing MCP, and then immediately started talking about Skill. Many people who see this term for the first time will instinctively treat it as another new protocol or another advanced prompt.

My judgment is very straightforward: Skill isn’t here to replace MCP; rather, it’s more like providing an occupational manual for the agent. MCP solves the problem of “enabling the agent to connect to the external world,” while Skill solves the problem of “how to reliably get the job done after connecting.” These two are not a replacement relationship; they are more like one following the other.

Simply put, MCP gives the agent hands and feet, and Skill tells the agent not to mess around.

I recently went back and reviewed the articles in my blog related to AI from the past two years, and I found that the content is no longer just simple experiences like “whether a certain model is good or not.” Instead, it has gradually formed a relatively clear main thread: How AI truly entered my development workflow, and what efficiency gains, costs, and new constraints it brought.

Recently, in the project, there has been heavy use of AI programming, which should be the most integrated AI in work over the past three years. The notes taken were not systematic; whatever came to mind was recorded.

Background

Linux environment, backend service development, without involving any UI or frontend content.

Models

I’ve tried out the three “Big Three” in China – minimax, glm, and kimi – and kimi has performed best. claude effectively handles large requests by breaking them down, while codex is most suitable for production environments; it’s exceptionally cautious.

Cultural Propagation: Its ideological influence, subtle and pervasive. AI Programming: Not performing software design, resulting in a lot of rework.

Cultural Propagation

Initially, the project only supported English, Japanese, and Korean. Thinking it was just AI translation, we wondered if supporting more languages wouldn’t be a good idea. So, French, Russian, and Hindi were added. At this point, no problems were detected; when the program executed translations, formatting issues arose due to historical code problems, requiring re-translation of archived articles.

It seems like another year has passed, and the biggest change at work is a significant increase in AI participation. Previously, switching between different development languages required developers to be familiar with various language-specific API interfaces. Now, these basic code snippets can all be generated by AI, which is a huge blessing for developers.

ChatGPT

As early as 2023, I’ve written two simple introductory articles about it. Now it’s been 25 years – how to put this… I haven’t felt a significant improvement. It still needs to develop its own cognition, be able to reasonably break down tasks, and, of course, most importantly, identify whether AI-generated code contains bugs.