Ai

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.

Recently, I’ve been migrating some edge cases to MiniMax and local models. The more I use them, the more I feel that we shouldn’t always measure things by the standard of “the most powerful model.”

My judgment is straightforward: don’t force weak models into hard tasks. Models like MiniMax are indeed limited in capability, but for complex coding, long-chain reasoning, or ambiguous requirement decomposition, they fall a bit short. However, if you ask it to do data cleaning, document writing, or searching for proposal materials—these kinds of tasks—it can handle them perfectly well. The same logic applies to local models around the 12B size; translation, format rewriting, and batch cleaning are actually where they are best suited.

To put it plainly, it’s not that the models lack value; it’s just that we shouldn’t place them in the wrong roles.

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.

Throughout March, I was constantly testing between various large model API hubs. It is indeed cheap. You can test out foreign models like ChatGPT, Claude, and Gemini for a small amount of money per month, which at first glance seems like finding an extremely cost-effective solution. However, after actually using it, I increasingly feel that this path has always been constrained by an impossible triangle: Quality, Stability, and Affordability—it is difficult for all three to be achieved simultaneously. By last weekend, the situation became quite clear. During the two days from 2026-03-28 to 2026-03-29, I felt a noticeable tightening of risk controls on ChatGPT channels, and Claude was no different. Many low-cost relays that were previously usable suddenly became unstable or even completely failed. For me, this basically signaled the temporary end of the low-cost API relay model.

Recently, I’ve been observing discussions within the industry, and it seems there’s been a fundamental shift in the definition of “growth.”

Previously, when we discussed the internet, we talked about “four ounces moving a thousand pounds” – writing a few lines of code, renting a few cloud servers, and leveraging excellent interaction and operations to unlock hundreds of millions of users. However, as of 2026, this “low-asset” illusion is being completely shattered by large models.

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.

Recently mingling in various programming large model communication circles, the most complained about thing is model degradation.

• Models deployed on local desktop computers are quantized models, essentially downgraded versions.
• With “vibe coding” so popular, could it be that the content output by current large models is the most valuable product – code?

“Previously, it was mentioned that when logging into Gemini Cli, you needed to configure the Google Cloud Project ID. This is already wrong – if it’s a personal account, there shouldn’t be this restriction. The fact that this restriction exists indicates that you’ve started triggering Google’s security system and are being identified as not being a personal account.

It’s frustrating; after using it for half a month and getting used to it, now I have to return to the embrace of cc + domestic models.”