DEV Community

Most advice about getting better output from Copilot is advice about phrasing. Be specific. Give it context. Ask it to think step by step. That plateaus quickly, and it plateaus for a structural reason: better phrasing asks the model to try harder. It does not tell the model anything it did not already know. The thing that actually moves output is a file. .github/copilot-instructions.md , committ…

Two Posts With Holes In Them For two and a half weeks, two posts on this blog referenced diagrams that did not load. Not a rendering quirk — a 404. Each post pointed at its diagram by bare filename, something ending in -diagram.svg , with no domain and no leading slash in front of it. That is a relative path. Ghost renders the markdown card verbatim, so the browser resolved that filename against …

When I audited my own SaaS subscriptions by hand, I found 7 tools I remembered paying for. A scan of my mailbox found 23. The gap between those two numbers is the entire reason SaaSClerk exists, and this post is about how the scanning engine works: the architecture, the trade-offs, and the parts I got wrong first. The core problem An email mailbox contains every receipt, renewal notice, and price…

Hi DEV! Pasting a document into a translation site works right up until the formatting matters. Then you get a wall of text back and rebuild the layout by hand. And if the document is a contract or a medical letter, you have just uploaded it to somebody else's server to save yourself ten minutes. LingoGeek translates the file rather than the text: .docx comes back as .docx, with headings, tables …

Every few months another demo shows an AI agent opening a pull request that closes a bug ticket, and the reaction is the same: impressive, and also — would you actually trust this in production, unattended? Most teams' honest answer is no, and the reason isn't model capability. It's that closing the loop from "bug reported" to "fix merged" without a human in the middle requires solving a problem …

I am building a site whose entire job is to be quoted by AI assistants. It is the marketing site for SearchD , an answer engine optimization practice, which makes the site both the product and the test case. Three things get recommended everywhere for this: let the AI crawlers in, publish an llms.txt , ship JSON-LD. I implemented all three. Then I went looking for evidence that each one does what…

I build the whole argument walking the dog. Beginning, middle, the objection someone will raise, my answer to it. It is all there. I get home, open the editor, write the first sentence — and the second one does not come. I did not forget the subject. I forgot the sequence , which was the only hard part. The easy explanation is speed: people speak three to four times faster than they type, so the …

Sometimes a WordPress plugin or theme update completes without a single PHP error, the admin screen reports success, and yet the live site looks broken the moment you open it. A changed CSS load order, an overwritten font declaration, a clashing class name — these can silently wreck the layout without ever touching an error log. Because nothing throws, nothing gets logged, and nobody notices unti…

The original Omegle proved something for fourteen years: two strangers who would never have met can have a good conversation. It shut down in 2023. What it never solved is the part I kept running into myself — most of the world still can't understand each other. You get matched with someone in São Paulo or Jakarta, you both say "hi", and that's where it ends. So I built Veilr: a random chat — tex…

Green started as a small experiment. 🌱 I didn't have a big roadmap. I just wanted to build a PHP framework myself and understand more of what happens underneath the frameworks I use every day. The first version was simple. I wasn't trying to build something that could compete with existing frameworks. I was mainly interested in the process of building one. Some parts were there from the beginning…

Originally published on tamiz.pro . The rapid adoption of agentic AI in software engineering has introduced a new class of operational risks: autonomous agents that can interpret, execute, and commit code. While powerful, these systems lack the inherent safety rails of traditional deterministic software. When an LLM agent makes a cascading error in a code review pipeline, the "blast radius" can e…

Short answer: keep a manual DNS console for a small, slow-changing portfolio; build a provisioning pipeline when tenant subdomains are part of a repeatable property-management workflow and a missed record can block move-in. The dividing line is not a magic tenant count. It is whether you can test intent, publish records safely, observe propagation, and reverse a change without guessing. Here is t…

Last time I wrote about handing a monitoring script exactly one root command . This post is the same question ― what do you let unattended automation touch? ― aimed at a different target: the plumbing that carries audit reports and improvement plans written by Claude Code itself into my human-facing Obsidian wiki. The gate I ended up with takes 12 Markdown files as input, lets 4 through, and refu…

TORchIM Desktop v0.1.4.161 Alpha is out. This security-focused release updates bundled C-Tor to 0.4.9.12 and lyrebird to 0.8.1. Windows x64 portable builds were tested on Windows 10/11. Update recommended. https://github.com/architector-dev/TORchIM-public/releases/tag/v0.1.4.161 #TORchIM #Tor #CyberSecurity #P2P

Reading about monitoring is one thing. Getting an actual alert to land in your inbox at 2am — well, in my case, on demand, during a test — is another. I wanted to understand observability the way an SRE actually experiences it: not as a diagram in a slide deck, but as a pipeline you build, break, and fix yourself. So I set out to build a minimal but complete monitoring and alerting stack: Prometh…

I Built a RAG Document Assistant with FastAPI, React, FAISS and Ollama I've been learning more about Retrieval-Augmented Generation (RAG), and I wanted to understand what actually happens inside a RAG application. So instead of building another simple chatbot, I decided to build a complete application around documents. The result is CloudRAG : https://github.com/abderaoufsec/CloudRAG What does it…

This article provides a step by step guide to two small Rust CLIs that ask a self-hosted Gemma 4 E2B the same question. The first calls the model's OpenAI-compatible HTTP endpoint directly. The second is an MCP client: it launches the rig's own MCP server and asks through its tools. https://github.com/xbill9/gemma-rust https://github.com/xbill9/gemma-rust-mcp What is this project trying to Do? Bo…

I don't think AI is going to end humanity/civilization in the next decade. Personally, I feel like the doomsday buzz about AI now is probably what was there when the internet first came live... Imagine how the first phone call must have felt...

Picture the ordinary version of this. You ask an AI assistant a question that actually matters — about a refund policy, a dose, a tax rule, a contract clause — and it answers with the fluent confidence these tools always have. You act on it. It was wrong. Now you are out of pocket, or worse. Whose problem is that? The answer-first version is unsatisfying but honest: it depends on where you live a…

Last week I published a post about nine measurement bugs I found in my own evaluation harness , all of which happened to favour my results. Two readers replied with things I hadn't found. Both were about my checks rather than my numbers. I verified both and fixed both. My results did not change at all. That turned out to be the interesting part. Reader one: a canary that could not detect what it …