Articles
Industry news, technical articles, and product introductions
📚 Claude Tutorials Hub
40+ step-by-step Claude guides — prompt engineering, Claude Code, API, agents. Browse by topic →
Loading...
GitHub Actions Fails Quickly with Connection Reset: The Cross-Border Pitfall When Overseas Runners Pull Alibaba Cloud ACR
GitHub Actions build fails two seconds after starting at load metadata, reporting failed to fetch oauth token: connection reset by peer, with the error pointing to the FROM line in the Dockerfile. Don't change the code—this is an intermittent interruption in the cross-border link from overseas runners to the Alibaba Cloud ACR authentication service. This article provides criteria, a workflow with automatic retries, and a structural solution.
developerAug 5, 20264 min
63
Auto-Generating Daily WeChat Covers with MiniMax: A Production Pipeline Postmortem
We automated our newsletter's daily WeChat cover: MiniMax image-01 renders a marketing-style background, an SVG text layer composites the headline, sharp crops to the exact 2.35:1 ratio, and Playwright drops it into the WeChat draft. The full postmortem covers why AI must never draw the title text, how one 'negative space' prompt word shoved the subject out of frame, and how word-splitting line breaks got fixed — with three real before/after images.
prompt-engineeringautomation+6
ai-tutorialsAug 5, 20266 min
125I Put My Opus 5 Config on the Recommended Diet, Then Ran 18 A/B Trials: 21% Cheaper, and I Can't Prove It's Better
"Opus 5 verifies itself, so delete your fallback prompts" is advice you hear everywhere. I took it, then isolated both configs with CLAUDE_CONFIG_DIR and ran 18 headless trials on identical tasks. Output tokens dropped 21% and wall clock 20-29%, with zero counterexamples. But two of the rewritten rules never fired at all, and one result points the other way: the old config's most thorough run covered a strict superset of what the new one found. Why cheaper and better are separate questions.
prompt-engineeringclaude-code+4
claudeAug 5, 20266 min
182That npm install You Ran Yesterday May Have Stolen Every Key You Own
A supply chain attack on keyv and 10 related npm packages infected 434 packages with 2B+ monthly installs. The worm steals npm tokens, GitHub PATs, AWS credentials, Kubernetes secrets, and more. Plus: why the Airtable acquisition is the same risk in business clothes. Five things to do right now.
developerAug 5, 20265 min
76DeepSeek V4 Pro vs Flash: I Ran 5 Hard Tests. Here's What 12x Gets You.
Here's the short version: **Pro is worth it for agent workloads. Flash has a hidden token-eating habit you won't notice until a long task eats your context.**
toolsAug 4, 20268 min
277Half My openclaw Commands Ran, Half Didn't — It Looked Like a Permission Classifier, It Was launchd
Same machine, same user, same global config. Two Claude Code windows running the same CLI — one worked, one didn't. The obvious suspect was the permission classifier, which really does block commands. But the cause sat a layer down: the daemon's plist was installed and never loaded, so every gateway-bound subcommand died while purely local ones printed fine. That half-working shape is what sells the permission theory. Full trace, including the hypothesis I got wrong by misreading my own logs.
permissionstroubleshooting+4
developerAug 4, 20267 min
106Running a 70B Model on a 4GB GPU: Hacker Dreams vs. Engineer Reality
70B on a single 4GB GPU, or small models at scale on the edge? AirLLM and Cloudflare show two roads to cheaper inference. A no-hype comparison of what each trades, and where each fits.
developerAug 4, 20264 min
106MCP Config Generator: How to Write a Correct mcp.json for Claude Code, Cursor & VS Code
How to write a correct mcp.json for Claude Code, Cursor, VS Code and Claude Desktop: file locations, root keys, stdio vs HTTP transport, the #1 command/args mistake, and how to validate configs without committing API keys.
developerAug 3, 20265 min
140How Much VRAM Do I Need for a Local LLM? (2026 Guide with Calculator)
How much VRAM do I need to run a local LLM? This guide breaks down the four factors that decide it — weights, quantization, KV cache, and overhead — with a rule of thumb (0.6 GB per billion params at Q4_K_M), real examples (DeepSeek R1, Kimi K3), and the exact math from our free LLM VRAM calculator.
developerAug 3, 20265 min
242Your Terminal Just Got a Brain: Local Inference Is Crossing the Threshold
Three releases in one week—Reasonix, ds4, and Kimi K3 on AMD MI355X—all pointing in the same direction: LLMs are moving from cloud APIs to persistent local processes. Here's why it matters and what to do about it today.
developerAug 3, 20265 min
128Stacked PRs Are Finally a GitHub Feature — 10-Minute Setup
GitHub shipped gh-stack, making stacked pull requests an official workflow. No more third-party tools, no more long-branch hell. Quickstart + gotchas inside.
developerAug 2, 20264 min
176I Added Real IP Support to Nginx and Killed My VLESS Node
Three lines of nginx config for real client IPs took down an entire VLESS node. This post breaks down PROXY protocol asymmetry, over-trusted real_ip ranges, and stream-vs-http module confusion — with working config templates and verification steps.
developerAug 2, 20265 min
105