Don't Let Claude Review Claude's Code. Models That Think Alike Make the Same Mistakes
LLM judges favour models that make the same mistakes they do, and stronger models' mistakes converge. One vendor writes, another reviews, you read the diff.
Tutorials
Building a Flutter client for Hermes Agent on a foldable
How we built Pomelu, an open-source Android and iOS app for self-hosted Hermes Agent: the gateway protocol, turns that survive a dropped connection, streamed Markdown, foldable lay...
An Engineer's Guide to WebMCP in Chrome 156: How In-Browser Tool Calling Actually Works
Part 1 of a multi-part series on WebMCP, browser agents, and web platform security. By Damisile...
What I learned building a lossless token compressor for Claude Code
In a long Claude Code session, most of what gets sent to the API isn't your prompts. It's tool...
49 minutes from first commit to production: building a planning poker app with Claude Code
My team estimates stories with planning poker. For a long time we used a free site that was covered...
GitHub Universe 2026: Announcements, Sessions, and My Technical Takeaways
I attended GitHub Universe 2026 in person at Fort Mason in San Francisco. The keynotes alone packed...
The browser inside your AI editor is not a browser. Here is the check.
Forever Security's EMBRACE research (2026-10-29) shows the preview browsers in five AI coding tools break the three rules a real browser keeps, so a local HTML file can read your k...
Before git worktree, git-new-workdir Symlinked .git and gc Couldn't See Its HEAD
Before git worktree, a 2007 script shared .git through symlinks and gc couldn't see the other checkouts. Why five agents' detached commits survive gc now.
Automating the AWS Console with an AI Agent: Everything Worked Except Four Save Buttons
What I did As part of a server migration, I let an AI agent drive its built-in browser...
How to Stop a Model Picking the Wrong Fact From a Long Prompt
A model reading a long prompt favors the passage that best matches your question, true or not. Long prompts hurt mostly because they carry more look-alikes, so keep those out and a...
My RAG isolation tests still passed after I deleted the security filter
I built Atlas AI, a private copilot where you upload documents, ask questions, and every answer cites...
How to check whether AI crawlers can actually read your site
Getting a site online is easy now, but getting found takes much longer, and more of that happens...
Don't Write Markdown Files for Your Coding Agent. Write Scripts.
If you want agents to do what you want, you need to learn how to box them into deterministic actions....
Same correct total, 69% fewer tokens: what a shopping agent spends on WooCommerce
We ran 110 shopping-agent trials on WooCommerce. On complex tasks, KaliCart Bridge used 69% fewer tokens than the Store API and cut median time from 81s to 39s.
The ten-hop chain was two keys taking turns
I went looking for the deepest reference chain in my ledger and found one ten hops long. Every edge...
Pamyo: a séance for your codebase, where a local Gemma 4 may only quote the developers who left
I built this for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine, but it...
The Chunking Dilemma: Why RAG Fails Before Retrieval Even Starts
Hey friends! Welcome back to our ongoing series on building real-world, production-grade...
I built a Claude Code skill that makes video ads without a video model
How I built reel-studio, a Claude Code skill that makes Reels and TikTok ads: deterministic HTML motion, Playwright frames, ffmpeg loudness, Whisper captions.
Why upscaling old low-res video makes it look worse, and the ffmpeg filters that fix it
If you've ever run an old 240p YouTube rip or a 2012 phone video through an AI upscaler, you've...
How I built editable personality for my desktop AI companion: a character card that shapes wording, never facts
How I built editable personality for my desktop AI companion: a character card that shapes...
The Most Dangerous Bug in AI Isn't in the Code. It's in Our Definition of Winning.
From a tragic football collision to the AI race: what should responsible developers do before warning signs become human tragedies?
Как и чем ИИ может помочь разработчику с опытом более 25 лет?
1. Введение: парадокс опытного разработчика Когда я вижу очередной заголовок «ИИ заменит...
Safe Tools, Unsafe Session: Why Agent Permissions Need History
Taint tracking for AI agent tool calls: per-tool allow/deny rules miss the lethal trifecta, so TaintGuard gates Claude Code by what the session has read.
How to Test Your LLM App for Prompt Injection: A Practical Starter Kit
Every platform shift in enterprise computing has followed the same script. Mainframes, client-server,...