工作流

How to Rescue Claude Code Sessions Stuck on Image Dimension Limits Recently I hit a confusing error in Claude Code: An image in the conversation exceeds the dimension limit for many-image requests (2000px). Start a new session with fewer images. The screenshot I’d just pasted was completely normal—just 100×200 pixels. By intuition, this should mean “the last image is oversized,” but it wasn’t. This is a cumulative bug with counterintuitive trigger conditions, root causes, and fixes. Once you hit it, you keep hitting it. This post explains the rules, the mechanics, and ready-to-use tooling to fix it. ...

Most people have tried voice input and given it up—what comes out is a jumbled mess, takes time to clean up, and ends up slower anyway. That’s the old voice recognition problem. Typeless adds an AI layer on top of transcription to polish it, which basically solves it. From using it, three scenarios stand out. Scenario One: Drafting Technical Articles The most time-consuming part of writing technical articles isn’t typing—it’s the “from idea to first draft” phase. You have the structure in your head, but translating it into words hits a wall. You keep deleting and rewriting, and the whole thing just slows down. ...

You’ve bought a VPS and written quant strategy code, but how do you get it to “run automatically” and “tell you what’s happening at any moment”? That’s where most people get stuck. I solved this with OpenClaw. What is OpenClaw Simply put: a framework that lets AI assistants call various tools. Its core capabilities are: Provides CLI tools (openclaw message send) to send Telegram/Discord messages from any script Has a Skill system to equip AI with various capabilities (GitHub, Notion, weather, custom scripts) Supports cron scheduled tasks and remote triggering For quant trading, the most useful part is message push notifications. ...

I’ve been using Claude Code—Anthropic’s CLI tool—to manage my fleet of servers since last year, and it’s genuinely changed how I work with infrastructure. This is what AI should be doing: not chatting, but actually getting things done. My setup 9 overseas VPS instances (AWS / DMIT / Tencent Cloud), distributed across the US, Hong Kong, Japan, and Singapore, running: Proxy nodes (Xray + Hysteria2) Quantitative trading strategies Monitoring stack (Prometheus + Grafana) Various automation scripts I used to SSH into each machine manually. Now I just tell Claude Code “update the Xray config on the Japan machine,” and it handles the SSH connection, modifies the config, restarts the service, and verifies it’s working. ...