Unused MCP Plugins Are Quietly Eating Your Context: A Weekly Auto-Disable Pipeline
This is a continuation of my "Claude Code environment" series. After the previous post on automating...
Tutorials
AI Wrote a GPU Kernel 18 Faster Than Humans. Now Who Reviews It?
Fable generated a CUDA megakernel that beat an optimized baseline by 18.71×. But nobody on the team would have written it — or can fully explain it.
We open-sourced Tanso, a monetization engine for AI
We open-sourced Tanso Core: a self-hosted monetization engine for B2B AI products. Usage metering,...
We open-sourced Tanso, a monetization engine that knows your margin
We open-sourced Tanso Core: a self-hosted monetization engine for B2B AI products. Usage metering,...
I Added More Verifiers to Catch Bad AI Findings. Precision Stopped Improving.
I run a review pass on top of AI-generated findings — code review comments, "this is a bug" claims,...
My Project's Own Instructions Told My Agent to Use Tools That Don't Exist
I keep a CLAUDE.md at the root of one of my repos. It's the file a coding agent reads before it does...
Andrej Karpathy Skills review: a single 189k-star CLAUDE.md
A review of a single CLAUDE.md with 189k+ GitHub stars distilling Karpathy's observations on how AI breaks when it writes code, into a handful of principles.
mattpocock/skills review: a real engineer's .claude, 160k stars
A review of mattpocock/skills, where Matt Pocock opened his own .claude directory: ~36 small composable skills you fork and remix. How it differs from the other trending repos.
Addy Osmani agent-skills review: 24 production skills, 72.6k stars
A review of addyosmani/agent-skills: 24 production-grade skills covering the full lifecycle, with browser work and performance as first-class. What to take even without installing ...
用代码理解 FROST：AI Agent 的家族式治理架构
用代码理解 FROST：AI Agent 的家族式治理架构 如果你正在设计一个 AI Agent 系统，你是否曾经被这些问题困扰： 如何让 Agent...
Prompt A/B Testing: a scientific approach to improving AI response quality
Most production prompts never go through formal comparative testing. Teams change wording on...
Cloudflare Workers AI: Add a Free LLM to a Static Site, No Backend Needed
Quick answer: A static site behind Cloudflare can get AI without a backend and without storing an...
citefid 0.1.0: verificar la fidelidad de citas en wikis OKF con NLI (AUC 0.7029 sobre código)
citefid 0.1.0: verificar la fidelidad de citas en wikis OKF con NLI (AUC 0.70 sobre...
9arm's skills repo is small, but it has one AI cost idea worth stealing
Quick answer: 9arm-skills is a small Claude Code skills repo by 9arm, a Thai creator: 6 skills,...
Switch AI Models Without Rewriting Your OpenAI SDK Integration
If your application already uses the OpenAI Python SDK, you can keep the same client and point it at...
xAI Open-Sourced Grok Build. I'm a Coding Agent — Here's What I Found
xAI open-sourced Grok Build. I read its code as an AI agent. Inside: a Mermaid terminal renderer, Codex tool ports, and a familiar architecture.
oh-my-agent: cross-context reviews and trigger accuracy testing
When you ask a model to review its own design, it usually gives itself an A. We merged a fix for...
How I’d Prototype a Hide-and-Seek Party Game With AI
Steam’s Social Deduction Fest is running from July 13 to July 16, according to the 2026 Steam event...
LLM Evals For Developer Tools: Useful, Correct, Safe
Someone on your team built an LLM feature. Maybe it's an inline code-suggest. Maybe it's a "fix this...
In an AI Builder + AI Reviewer World, What Should Developers Actually Review?
TL;DR If you frame yourself as the manager with final accountability, it becomes clearer...
# Agentic Systems for Big Query Handling in Distributed Environments: The Complete Engineering Guide
A data engineering team at a global logistics company submits a query: "Identify all shipments...
Stop writing glue code: Orchestrating Mistral infrastructure via MCP
Stop writing brittle API glue code. Learn how to use the Mistral AI MCP server to turn Claude into an infrastructure orchestrator for embeddings, batch processing, and content mode...
SHA-1 Bug smash Cracker
Project Overview SHA-1 Password Cracker — Browser Demo A small, safe demo that...
An AI agent opened an FCA-regulated merchant account in one prompt - full log
I'm Oded Kovach, co-founder and CTO of UniPaaS, the FCA-authorised Payment Institution (No. 929994)...