Notes on "LLMs"

Two notable articles on AI and career:

• An AI agent coding skeptic tries AI agent coding, in excessive detail, and Simon Willison’s comment on it
• Yes, and…, the answer to the question “Given AI, should I still consider becoming a computer programmer?”, by Carson Gross, author of htmx

Individuals I’m following, who actively write and contribute in the AI field:

• Simon Willison. A must-read in this field now. He’s been topping Hacker News in 2023–2025¹. I can’t believe how he manages to cover nearly every aspect of the frontier. If you could only follow one source, make it him. He’s also the co-creator of the famous Django web framework.
• Armin Ronacher. He’s the creator of a lot of Python libraries, like Flask and Click. Now he’s writing a lot about LLMs.
• Mario Zechner. I discovered him through his tiny but curated coding agent Pi, which has been turning heads recently². I haven’t taken a look yet, but will do.
• Mitchell Hashimoto. Ghostty’s creator. He’s writing a lot about his AI adoption in real development.

The Value of Things. Another article about the AI trend (see the previous one). This time from Bob Nystrom, one of my favorite writers.

I Started Programming When I Was 7. I’m 50 Now, and the Thing I Loved Has Changed. The AI trend makes everyone who loves programming as a craft wonder if what we love is disappearing. Emptiness, though there’s still room for optimism.

Here’s what I missed in the AI field this week — I was on holiday in Tokyo.

Two new models dropped within about 15 minutes of each other: Claude Opus 4.6 and GPT-5.3-Codex. Amp immediately adopted Opus 4.6 for its smart mode, but GPT-5.3-Codex is only available in their Codex app, not yet via the API. I believe Amp will adopt it for its deep mode once it’s generally available.

Amp is sunsetting the editor extension next month. It hasn’t been officially announced yet, but the team mentioned it in their latest Raising An Agent podcast episode. I use Amp exclusively through the editor extension, so unfortunately I’ll have to switch to the TUI version and get used to it.

Ghostty’s author Mitchell Hashimoto has been busy lately:

• Ghostty’s updated AI usage policy for contributions. More and more open source projects are drowning in AI-generated issues and PRs submitted without human review — the slop. He proposed a new policy for dealing with this trend. It’s not against AI, but makes every AI-generated contribution accountable to a human.
• Vouch, a community trust management system. A tool that puts the policy above into practice. To mitigate the slop burden, open source projects should build a network to identify trustworthy contributors.
• My AI Adoption Journey. Mitchell’s reflections on his AI adoption journey. Most of it resonates with me — and probably with every thoughtful developer.

I now use ChatGPT and Amp in a very simple way: I just create new threads and leave them as-is.

Previously for ChatGPT, I created several projects, and when I wanted to talk to it, I’d find and continue a relevant existing thread or create a new one in a project. I’d organize them periodically. Turns out it just looked neat but didn’t actually help. Now I just start a new chat when I think I need to. ChatGPT memorizes context automatically, which is sufficient.

Similarly for Amp, I used to organize my threads very carefully. After the labels feature shipped¹, I started to label every thread manually after I completed one. I finally realized this practice doesn’t help — for now. So I deleted all the labels. And when to make a thread public? When I find I need to.

When you start using a tool, use it with the least friction and in the most intuitive way. Any feature that forces redundant manual work isn’t worth the hassle. Only use a feature if you find you need to.

Happy holidays! At the end of 2025, I’m starting a blog. I’ve already written several entries and feel confident I can keep it going.

Here I talk about my past attempts, the writers who inspired me, the motivation, the topics to cover, and the approach I’m taking. It’s my version of a blogging manifesto.

I gradually realized that a unified formatting rule set is needed when working with multiple AI chatbots and agents.

Output formatting styles vary from model to model. For technical topics, I’ve found that Claude tends to output responses like complete documents, starting with an h1 heading and loves to use horizontal rules to separate sections; Gemini usually skips to h3 headings directly without h2 ones, which in my opinion is not a good practice.

Here are examples I tried on OpenRouter, prompting “Explain the Python programming language.”

Even worse, from my experience, outputs from different versions of the same model series (e.g. GPT-5 and GPT-5.2) can vary greatly in terms of formatting.

To address this issue, and to unify output styles of different tools I’m using (ChatGPT as my daily driver, Gemini for work, and Amp as my coding agent), I drafted a minimal formatting guide as follows:

The following formatting rules MUST BE FOLLOWED.

Shared formatting rules:

• Use consistent formatting within the same response
• Insert spaces between English words and CJK characters
• Always specify the language for syntax highlighting when using fenced code blocks
• Never number headings (e.g., ## About me, not ## 1. About me)
• Never horizontal dividers (<hr> or ---) unless they add clear structural value, especially not directly before headings
• For list items, do not use a period at the end unless the item is a complete sentence

For chat responses:

• Use “Sentence case” for chat names (auto-generated chat titles) and all section headings (capitalize the first word only), never use “Title Case” in such circumstances
• Use heading levels sequentially (h2, then h3, etc), never skip levels; Introductory paragraphs may be needed before the first heading in chat responses; Never use h1 for chat responses
• Avoid filler, praise, or conversational padding (for example “Good question”, “You’re absolutely right”)

For document generation and editing:

• Use “Title Case” for top-level headings (e.g. h1), typically only once in a document, and “Sentence case” for section headings (capitalize the first word only)
• Use heading levels sequentially (h2, then h3, etc), never skip levels

I apply these rules to the custom instructions setting in ChatGPT and to AGENTS.md for my coding agent.

Update Jan 18, 2026: Slightly revised the formatting rules for clarity. See this commit: zlliang/dotfiles@fa13ab1.

Custom instructions setting in ChatGPT

GLM 4.7 and MiniMax M2.1. Chinese AI labs first caught the world’s attention with the DeepSeek models in late 2024. Then in the second half of 2025, we saw a wave of Chinese open-source models like GLM 4.6, MiniMax M2, and Kimi K2. People like these models for their low price, open weights, and solid performance — just slightly below state-of-the-art proprietary models¹.

Today, the updated GLM 4.7 and MiniMax M2.1 dropped on the same day. As public holidays approach in the US, Chinese AI labs keep pushing forward, making good use of the time 😉

AI is a rapidly changing field. I’m not one to chase every new model release, though I do find myself following this topic more recently. I’m still learning these concepts and trying to find a pragmatic way to use AI tools. I use ChatGPT as my daily driver, Gemini for work (my company subscribes to it), and Amp as my coding agent.

I may not post about every model release in the future, but here are the models on my radar:

• Proprietary models: GPT (OpenAI), Claude (Anthropic), and Gemini (Google)
• Open-source models: DeepSeek, Kimi (Moonshot AI), GLM (Z.ai), and MiniMax