While setting up the Claude Science container, I learned about a new way of using NVIDIA GPUs inside containers, so I’m noting it down (most of it was written by AI, used as reference material for my own research).

The way I star GitHub repositories is pretty much the same as how I like and collect videos on bilibili: I just click them on a whim. Whenever I see a project that looks even remotely interesting, my brain always goes “might be useful someday” or “I’ll take a look later” — and my finger clicks the button before my brain finishes the thought.

That’s how, over the years, my star count quietly climbed past 800. To be honest, I have no idea what those 800+ projects actually are — most of them were starred because they seemed useful back then, and then never opened again.

I had already managed to get claude-science running in a container, and basic functionality worked without major issues. But when I wanted to do things like molecular docking, I couldn’t—the container simply had no GPU. However, when I pulled NVIDIA’s official image to build the container the same way I had before, something bizarre happened: every language kernel in CS—Python, Perl, R—stopped working, and the entire runtime environment was rendered useless.

This was truly beyond my understanding. After consulting Gemini manually with no luck, I decided to let opencode + deepseek-v4-flash handle it on its own—not me remotely typing commands and directing it, but an AI agent living inside the container that read the logs, bisected parameters, decompiled the parser, and edited the entrypoint itself. It was a strange and interesting experience; here’s a record of it.

Remember [that April post agonizing over device choices]? Back then I listed a bunch of candidates, weighed them one by one, and confidently declared I would “stick with the Fydetab Duo.” Well… it turns out humans can’t escape the universal law of zhen xiang (something you dismissed turns out to be great), and in the end I bought the MacBook Neo after all.

After previously tinkering with putting Claude Science into a Docker container, I’ve been using it relatively intensively over the past two weeks (connected to DeepSeek, not the original Anthropic version, of course), so I want to talk about its advantages and limitations.

I recently worked on a small project: putting the Linux version of Claude Science into a Docker container, paired with an API Bridge so it can run through third-party API backends without needing to hold an Anthropic API Key directly.

The process was more eventful than expected—also quite interesting. Here’s a record of it.

Lately I’ve been working on integrating several AI applications, which means I need to switch between different models. That’s when I discovered a problem — the APIs of OpenAI and Anthropic are incompatible.

Recently, I chatted with friends about the devices we each want to buy, and we all shared the same feeling — everything is getting more expensive. Game consoles, graphics cards, RAM, SSDs, even laptops that used to be relatively affordable — the prices now are enough to make anyone hesitate.

Yesterday I got an email from LeanCloud saying they’re shutting down service…. Wait, what?

I had been thinking that when my blog’s total page views hit 50,000 again, I’d write a celebratory post. Little did I expect that the clicks would grow much faster than I imagined — before I could even finish drafting the celebration, the number had already blown past it.