Documents Aren't Bags of Chunks
One thing kept bothering me about retrieval systems: they often destroy the document before...
Tutorials
Why Your AI Agent Is Reading 10x More Data Than It Needs
Everyone wants smarter AI agents. We compare models. We tweak prompts. We experiment with system...
A rulebook of how money code breaks, and an agent that refutes its own findings
Money bugs pass review Money bugs are rare per repository and expensive when they happen....
What is going on?
Playing the game of writing technical post was funny two years ago. Now, I am a mod and it is...
The 16.67ms Race: Mastering Real-Time 60 FPS Video Segmentation on Android
Imagine you are building the next generation of Augmented Reality (AR) glasses or a...
MCP Observatory: Scan, Test, and Secure MCP Servers Before Agents Depend on Them
MCP servers are becoming production dependencies. If an agent depends on a server, that server needs...
NarraMeuGol: the AI that calls your street-football goal 🎙️⚽
This is a submission for Weekend Challenge: Passion Edition What I Built NarraMeuGol...
Colibri: Running a 744B AI Model on Your Laptop
GLM-5.2 is a frontier AI model with 744 billion parameters. It normally requires H100 GPUs, hundreds...
Prompt Injection as a Control/Data Boundary Problem
A short structural framing for prompt injection, with an open-source POC using cryptographic boundaries and separate data/control planes.
I Built a Simple RAG App with LangChain, OpenAI, and Pinecone
Large language models know a lot, but they do not automatically know the contents of our private...
Weekend Challenge
Liquid syntax error: Tag '{% https://spiffy-pavlova-e7afad.netlify.app/ %}' was not properly...
An LLM agent just ran a full ransomware attack. No human operator.
Sysdig published the JadePuffer report this month and it changes the conversation about AI security....
I Built An AI That Roasts Me. It Hurt.
I built Roaster0 to roast anything. Then I fed it myself. Meet Roaster0 - my "Automated...
Stop Using LangChain for Simple LLM Tasks: The Raw Anthropic SDK Is Cheaper and Clearer
A post by Mudassir Khan
How to Use Claude Code Hooks (Turn Rules Into Guarantees)
Claude Code hooks run shell commands at lifecycle events — auto-format after edits, block protected files, audit every command. Config, exit codes, recipes.
Commit Chronicles—Your Obsession Leaves a Trail. Mine Gives It a Plot.
Snowflake fetches a repo's commit history, finds the one story in it with plain SQL, and narrates that single thread with Cortex. Six storylines. One card.
AI can't run your company yet. Here's the math, and what to automate instead.
A $250M AI-agent platform disclosed numbers that explain why full autonomy hits a wall at SMB economics in 2026, and why putting the grind on autopilot is the move that actually fi...
My SaaS was silently broken for 4 days because an AI My app was broken for four weeks and I didn't notice. So I got rid of the API.
On June 14th, the weekly brief feature of my product died. No crash, no alert, nothing in my inbox....
BMad Method vs AI-DLC: Two AI Development Frameworks Compared
AI coding agents are everywhere. ChatGPT, Claude Code, GitHub Copilot, Cursor, Amazon Q. They write...
HACKHAZARDS'26
Dial2AI: Making Generative AI Accessible Through a Phone Call No Internet. No Smartphone. No App....
Multi-Agent Systems Break at the Collaboration Plane | Focused Labs
Multi-agent systems fail when shared collaboration state disappears. Build a traceable collaboration plane for claims, findings, handoffs, and evals.
What do you use AI for the most?
At work, I use Claude, ChatGPT and Copilot, depending on the task I have. Sometimes I create my task...
Ever wish you had a personal drill sergeant or a dramatic movie narrator to hype you up before a big task? I built an app for that. 🗣️🔥 Built with React, Gemini, and ElevenLabs for the Passion Weekend Challenge!
I Built an AI That Yells at You (In a Good Way) Using ElevenLabs & Gemini DEV...
Build a RAG System in Google Colab Before Your Next AI Interview
You don't need to study machine learning for six months to understand RAG. You don't need...