Blog
Does AI-written code have fewer or more bugs
Wednesday, May 20, 2026 in Blog
Categories:
AI writes code so fast that bugs per line are surely lower, but lines of code explode, and requirements we used to skip now get cranked out, so bugs keep growing. Also, AI is unbeatable at finding others’ bugs—it surfaces even hidden ones. …
Recommend using claude code with domestic models
Monday, May 18, 2026 in Blog
Categories:
I actually have some aversion to the company anthropic, but it is currently at the height of its popularity, so I have to hold my nose and use it. I subscribed to a claudecode pro plan, but the quota is very small and can only be used for planning. …
The trick to using the GPT5 series models is to reduce restrictions
Friday, May 15, 2026 in Blog
Categories:
Someone shared very long and fancy prompts claiming to improve GPT5’s performance, which should be viewed with caution. Unlike the sonnet or opus4.6 and earlier models in claudecode, GPT5 is more noticeably negatively affected by randomly …
Tencent's model is much better than I expected, recommended to try
Friday, May 08, 2026 in Blog
Categories:
My main use case is writing code, and my projects are mainly command-line tools. Tencent HY3 Preview performs very well in my use case, with good instruction following and dialectical logic. I also tried Baidu’s CoBuddy coding model recently …
Recommended coding-friendly models to try
Tuesday, May 05, 2026 in Blog
Categories:
First, the old friend openrouter. After depositing $10, you get 1000 free calls per day. Most of the time there are a few decent models in the free tier. The official policy reserves the right to set an expiry on the deposited amount, which may have …
codex free auth automatic acquisition flow feasibility
Tuesday, May 05, 2026 in Blog
Categories:
I have two hundred free accounts and one plus account, connected to cliproxyapi, reverse-proxied for use in various CLIs. These accounts are enough for heavy personal use. If you enable 1M context, fast mode, use subagents, high-res image parsing, …
Why Raising Model Token Efficiency Allows Price Increases
Sunday, May 03, 2026 in Blog
Categories:
GPT5.5 is priced double compared to GPT5.4, and GPT5.4 is about 40% more expensive than GPT5.3codex. Both price increases share a fundamental logic: improved token efficiency. GPT5.2 is a painfully slow model, but the GPT5 series has high issue …
Sorry but mimo v2.5 pro really doesn't cut it
Sunday, May 03, 2026 in Blog
Categories:
Some people share that Xiaomi’s model can perform long-horizon tasks, executing hundreds of tool calls without errors. I don’t know who initiated this testing direction, but it’s like saying a student can hold their bladder for 100 …
Collected 34 vendors offering coding plans
Thursday, April 30, 2026 in Blog
Categories:
And obtained the time-to-first-token and token rate at 4 PM Beijing time for some vendors. Used it for a few months, welcome to visit and share your feedback! Project link: #https://github.com/jqknono/coding-plans-for-copilot
Xiaomi released token plan benefits
Thursday, April 30, 2026 in Blog
Categories:
Got a Xiaomi Pro Plan through my small project, trying it out this month. The project is a VSCode plugin that connects any chat-completion/responses/anthropic-compatible API to GitHub Copilot. Project address: …