Topic
664 articles found
Most authenticator apps force a flat security model. Every token lives behind the same unlock flow. We thought that was the wrong tradeoff. We’re a small team building LocalAuth, an open-source iPhone authenticator, and I’m the primary developer behind it. The project started as a small internal exp
Letting AI Control RAG Search Improved Accuracy by 79% Most RAG (Retrieval-Augmented Generation) search pipelines are built like this: Query → vector search → Top-K retrieval → dump everything into LLM This fixed pipeline is the root cause limiting RAG accuracy. A February 2026 ArXiv paper (arXiv:26
A Django traceback for a simple TemplateDoesNotExist error is 40+ lines. 35 of those lines are Django internals — django/template/loader.py, django/core/handlers/base.py, django/middleware/common.py. Your AI doesn't need to read Django's source to fix your missing template path. But it does, every t
Africa's Borders Have Stories Every city in East and Central Africa carries layers of names. Kinshasa was Léopoldville. Kisangani was Stanleyville. Lubumbashi was Élisabethville. Before all of those, they had indigenous names in Kikongo, Kiluba, and Lokele. These aren't just trivia — they're essenti
Five days ago, North Korean state hackers hijacked one of the most trusted packages in the JavaScript ecosystem, axios, with 100 million weekly downloads, and turned it into a Remote Access Trojan delivery system. The attack was live on npm for three hours. npm audit flagged nothing. If you ran npm
You read the onboarding wiki. You join your first few meetings. You nod along, follow the process — and still feel like you’re missing something. Everyone else seems to know how things really work, but no one’s said it out loud. Sound familiar? Every tech company has two sets of rules: the ones on t
"You Keep Using That Word" Dispelling Container Misconceptions at the OS Level Before we write a single line of code, we need to kill the buzzword fog. The marketing definition you have heard a hundred times: "a container is an executable unit of software with its dependencies bundled together." Tha
Recently, a riddle was posted by @francistrdev on 1st April on dev.to that presented a unique challenge: a multi-line poem obscured by Caesar shifts. Riddle me this DEV and MLH Community [April Fools] FrancisTRᴅᴇᴠ (っ◔◡◔)っ Apr 1 #discuss #watercooler #writing #community 40 reactions comments "Mixed-S
We are living in the golden age of personal telemetry. Our watches track our heart rates, our phones log our steps, and apps record every calorie. However, most of this data sits in "silos"—disconnected tables that tell us what happened, but never why. If you've ever wondered if that late-night rame
Originally published at heyuan110.com This is Part 2 of the Harness Engineering series. Most CLAUDE.md files are bad — not because people don't try, but because they optimize for the wrong thing. ETH Zurich researchers tested 138 agentfiles across multiple AI coding agents. The results: Human-writte
The strangest thing about Esquire Singapore’s Mackenyu piece is not the sentence, “The following interview was produced with Claude, Copilot, and edited by humans.” It’s the calm, workmanlike tone of it. As if an AI‑generated interview with a living actor is just another production choice, like swap
Originally published at heyuan110.com Your single OpenClaw agent worked great for two weeks. Then it started hallucinating project context into unrelated conversations, confusing coding tasks with writing tasks, and taking 15 seconds to respond because its memory index had grown to 200MB. The proble
Originally published at heyuan110.com Claude Code has three distinct extension mechanisms: MCP (Model Context Protocol), Skills, and Hooks. They look related on the surface, but they operate at fundamentally different layers: Hooks (bottom layer): Lifecycle event automation — "what must always happe
Originally published at heyuan110.com On March 19, Cursor shipped Composer 2 with a triumphant blog post. Three days later, a developer found kimi-k2p5-rl-0317-s515-fast in the API config. That single string unraveled a story about transparency, open-source ethics, and the global nature of AI infras
Originally published at heyuan110.com In February 2026, ByteDance released Seedance 2.0. Within weeks, it hit #1 on the Artificial Analysis text-to-video leaderboard — beating Google Veo 3, OpenAI Sora 2, and Runway Gen-4.5 in blind human evaluation. If you are reading this from outside China, you h
Here's a pattern you've probably seen: const results = items.map(async (item) => { return await fetchItem(item); }); Looks fine, right? Your AI assistant wrote it. Tests pass. Code review approves it. Then production hits, and results is an array of Promises — not the values you expected. The await
Organizational safeguards are now generally available in Amazon Bedrock Guardrails, enabling centralized enforcement and management of safety controls across multiple AWS accounts within an AWS Organization.
This Is What’s Really Hitting Your Website (Hint: Not People) I wanted to understand how much of our traffic was actually human, so I pulled and analyzed 48 hours of raw request logs. No filters, no analytics layer, just direct log data. Time Frame Start: 2026-03-31 10:00 UTC All requests within tha
Claude Code .claudeignore: stop leaking secrets and node_modules into your context If you've ever watched Claude Code read through thousands of lines of node_modules or seen it suggest changes to your .env file, you've hit one of the most overlooked configuration problems in Claude Code setups. The
