1,740 board runs, one human, a crew of AI agents: making Python up to 2,000 faster for Speed Demon 2026
My write-up for Speed Demon 2026 by Hackathon Raptors. The code is public:...
Tutorials
Knowledge graphs, explained for AI memory (and how Palace uses one)
Most AI memory systems today come down to the same recipe. Split text into chunks, turn each chunk...
Name your Claude Code sessions before you run more than one
you are looking at // Detect dark theme var iframe =...
Your Log File Can Hijack Your Agent: Sanitize Logs Before the Model Reads Them
Your agent reads logs written by your users, your upstreams, and anyone who can make your service print a line. Treat every log line as untrusted input and clean it before it reach...
How to Scale AI-Assisted Global Content Without Losing Local Relevance
Scaling content across countries has long created a tension between consistency and relevance. AI can...
Who is nondeterministic, the model or the human?
The fear of losing control over code is not new. When compilers appeared in the 1950s, many...
How to Build Your Own Google Antigravity Plugin: Packaging Skills, MCP Servers, Subagents, Rules, and Hooks
A practical, step-by-step engineering guide to packaging team workflows, MCP tools, custom agents, and deterministic guardrails into a single versioned Antigravity plugin.
A human approved her refund on Saturday. On Monday your AI told her refunds were impossible.
An HVAC company with eleven techs and one overworked office manager learned about this failure mode...
Keeping AI Agents from Writing Wrong Data: Validation, Deterministic Checks and Fallbacks in Go
An agent that answers a question wrongly is embarrassing. An agent that writes wrong data, such as...
We tested the viral AI chart model on dates it can't have seen. No edge.
Everyone is sharing a free AI model for stock charts. We tested it the boring way, on dates it cannot...
I Built an AI Team That Researches Stocks and Debates Investment Decisions 🤖
What if you had an entire team of AI agents researching stocks for you? Imagine one agent analyzing...
Building ArewaSafe: How We Used Gemma 4 & Disguise UX to Protect Highway Commuters in Northern Nigeria
How we built ArewaSafe (Kariya AI) — an award-winning travel-safety and community warning system for Northern Nigerian highways using Gemma 4, React Native, and ESP32.
Will this model fit on your GPU? Size a local LLM on paper before you pull it
When ollama ps shows a CPU/GPU split, your model did not fit and everything runs at the speed of system RAM. Parameters, quantization and the KV cache turn sizing into arithmetic: ...
Sharing system prompts across 3 AI clients in 64 lines of MCP
A 64-line TypeScript MCP server that serves one folder of system prompts to every AI client I use, plus the bugs I hit first.
The Context Window Tax: Why Autonomous Agents Choke on Raw Tool Responses (And How to Fix It)
When developers prototype their first autonomous AI agent, they usually focus on tool definitions:...
I built an AI tool that lets you generate pixel-art VFX
In order to make a pixel VFX art, just typing it in your terminal > Make a 32 px poison cloud...
How I Built a 3D Rubik's Cube Engine & AI Vision Solver in Flutter
From quaternion rotation math to edge computer vision: how I engineered CubeKing 3D from scratch using Flutter.
Is Your Mac's Python Is Too Old for Your MCP Server?
I built an MCP server that pulls my Oura Ring data into Claude Desktop. It's a small Python project...
Stop dividing by 4. I counted 951 texts and the rule is wrong both ways.
Most token guides say one token is about four characters, and a lot of code runs...
GitHub Octoverse 2026: AI Agents, Citizen Developers, and the New Security Reality
TL;DR Code is being written three times faster than anyone can review it: GitHub logged...
AI Agent Creation in 2026: A Technical Buyer's Guide to Frameworks, ROI, and Production Reality
AI Agent Creation in 2026: A Technical Buyer's Guide to Frameworks, ROI, and Production Reality The...
Which local model should a coding agent run?
One harness, same conditions, four dimensions, and the raw receipts of every call — this round, seven...
Running LLMs Locally on Consumer Hardware — Part 9: Image Generation on AMD, and a Creative Capstone
The final entry in a build-log series on local LLMs. Teaching a text-and-code team to make pictures meant getting ComfyUI and Stable Diffusion running on AMD hardware — a ROCm figh...
Hands-On AI Security: Red Teaming Piper with 5 Prompt Injection Vectors
Attack the Piper chatbot across 5 prompt injection categories, testing vulnerabilities, boundary...