Several Issues with Zhipu GLM-4.5 in Programming

Tue, 23 Sep 2025 10:24:43 +0800

Through some leaderboards and the report, I saw that glm-4.5 received high scores, so I gritted my teeth and subscribed to the annual coding plan.

However, while using the Zhipu glm4.5 coding plan, I encountered several issues that severely impacted my work efficiency.

Cline

In cline, there are roughly a few problems.

Problem One: Simple diff tool calls fail to output correctly.

Problem Two: The task list tool is unusable.

I once suspected it was a cline issue. But then I thought, deepseek, gpt-5, and claude-4-opus all work fine.

The prompt doesn’t change because of these. It’s most likely an issue with Zhipu glm-4.5.

Claude Code

Misunderstanding problems (unable to understand some simple natural language)
Incoherent responses, not listening to the user, failing to identify the target.

Later, if I find similar situations, I will add screenshots to this blog post. I don’t want to waste more time on this.

There’s also a common issue: obsequiousness.

Stopped Responding

A new problem encountered on 2025-10-03: it stopped providing feedback while answering a question and terminated the process.

The most likely cause of this problem is a lack of adaptation to the thinking interface, resulting in it thinking but not displaying the content.

Summary

Based on my current experience, among domestic AIs, apart from DeepSeek, the other major players tend to have unstable model outputs.

Without a doubt, Anthropic is the leader in this field.

I genuinely doubt the friends who told me Zhipu is good—have you actually used AI for programming? If so, how do you tolerate these issues? How has your efficiency improved?

If you think these problems are inevitable, then I sincerely suggest you use Anthropic’s products and models.

Aside

I really don’t want to use glm anymore, but there’s no choice—I’ve already paid for the annual subscription, and it’s non-refundable.

Therefore, as a user, you can only hope that glm will update its model.

As a consumer or customer, this feels very uncomfortable. It’s okay if the product isn’t fully developed yet; just don’t release it, or don’t charge for it like this. At 200 yuan a month, I might as well put all that money into deepseek. That’s a model that truly stands up to scrutiny.

Getting a refund is troublesome. I think reporting it to the consumer association could solve the problem to some extent. But it’s a waste of time. Furthermore, continuing to use it is a sunk cost. Therefore, I can only do this: I will not spend another cent on Zhipu in the future.

Update

Very strange!

Not long after I published this article, I found that the usability of glm-4.5 has become significantly better.

If you’re interested in experiences with other AI coding plans, you can read my other articles:

I Bought the Kimi Coding Plan Again - Experience and configuration methods for the Kimi monthly plan.
Doubao doubao-seed-code Test - In-depth testing of ByteDance’s Doubao coding plan.

Try Cline

Sun, 06 Jul 2025 10:29:43 +0800

I’ve been a long-time user of Cursor, but I recently discovered that Cline is also incredibly effective, especially when using its tool-calling capabilities via OpenRouter.

Cline is a VSCode extension that performs operations similar to Cursor’s “Agent” mode. If you’re not familiar with Cursor yet, I recommend checking out this introductory video:

What sets Cline apart is the ability to choose your own underlying model. For instance, the popular Kimi K2 can be configured via API. Today (2025-07-06), I tested Cline’s editing capabilities, and the results were much more organized and powerful than I had anticipated.

Transparency and Context

One major advantage of Cline over Cursor is transparency. You can clearly see exactly what context is being sent to the model.

The Test Task

I assigned Cline a task involving Windows APIs and tool usage:

1

Help me create a Windows desktop project written in C# that can configure Windows network settings to either use DHCP or a static IP with gateway and DNS.

The Workflow

The overall process was quite smooth, though I did hit one major roadblock: the application would crash immediately after initialization.

The issue turned out to be null variables during application startup that weren’t properly loaded via the XML manifest.

Ultimately, I used a combination of Cursor and VSCode to fix it. Cursor suggested using Visual Studio’s specialized editor rather than just the dotnet CLI, which allowed me to identify the null variable and resolve the crash.

The Cost Factor

While Cline’s file manipulation is impressive, the cost is a significant concern:

In a single morning of work, I spent $3.17 USD without even completing the task.
Given my usual programming schedule (about 4 days a week), two weeks of using Cline would already exceed the monthly subscription cost of Cursor.
Unless Cline can demonstrate a decisive advantage, Cursor remains the more economical choice for my workflow.

Cline on Svtter's Blog