Your Tenth Ship Is Always Someone's First
I ship MCP servers and agent automations constantly. Personal infrastructure, benchmarks, cron-driven...
Tutorials
An AI tutor that is not allowed to lie about circuits
The model proposes, the engine disposes. Verifying every LLM-built circuit against the real simulator before it reaches the canvas.
I Built a Dead-Simple API Gateway for My Local LLMs in 50 Lines of Python
I Built a Dead-Simple API Gateway for My Local LLMs in 50 Lines of Python I run three...
Run Qwen Coder & DeepSeek Locally: The 2026 Free AI Pair-Programmer Setup
You're paying $10 to $20 a month for Copilot. You don't have to. A 2024-era laptop can run a coding...
#04 – Modules & Modern Python Project Structure
Welcome to Day 4! Today is all about clean architecture, dependency isolation, and modern Python...
Your eval pass rate is 98 percent. Your confidence interval is probably wrong.
TL;DR. Almost every eval harness reports a pass rate with an error bar, and almost every one of those...
How We Built a Neuro-Symbolic AI Platform for the ASEAN AI Hackathon 2026
Originally published on my personal engineering blog at louvincentbaroro.me. At the ASEAN AI...
I auto-published 2,300 AI articles. Google buried 90% of my traffic.
This is the first post on this blog, and it exists because of a failure. So let me start there...
Why AI audit logs break when the facts change
Most AI agent audit logs can tell you what prompt ran, what model answered, and which tools were...
Founding Lead Playbook: Running Product, Architect & Engineering with AI Agents + 2 Humans
There are a lot of shallow "10x with AI" threads out there. This isn't one of them. This is the...
How I Debug a Misbehaving AI Coding Agent: My 4-Step Playbook
TL;DR AI coding agents don't fail like normal software — they fail confidently, and the...
How I Built My Site With Claude Code
I built this website from scratch over about three weeks of actual work. A week during holiday, a...
DiffusionGemma: The Developer Guide
Following our announcement in our launch blog post, we are sharing this developer guide to help you...
I built a profitable SaaS in 32 days without writing code, got paying customers, then open-sourced everything
A month ago, I put the entire codebase of my SaaS on GitHub under an MIT license; payments logic,...
Deploying a LangChain App on a $5 VPS: A Step-by-Step Guide
Deploying a LangChain app on a $5/month VPS was an experiment born out of necessity. Working in...
AI memory가 자기 출력을 다시 입력으로 세지 않게 하는 법
AI memory 시스템은 대화에서 기억을 만들고, 그 기억을 다시 요약해 더 높은 수준의 결론을 만들 수 있습니다. 여기서 원본에 가까운 입력과 시스템이 만든 파생 결과를 구분하지 않으면, 파생 결과가 다음 작업의 trigger를 키우는 self-reinforcing loop가 생길 수 있습니다.
I Tested 7 AI Memory Products for Portability - All 7 Lock You In
Picture a team that has spent 18 months working inside Claude Projects. Hundreds of conversations,...
MCP Series (07): Enterprise Deployment — Security, Authentication, and Version Management
Three Gaps Between Local and Production A local MCP Server takes one command: python...
Trusting an LLM's JSON in production
The layer between 'the model usually returns the right shape' and 'the rest of my system can depend on it' — schemas, validation boundaries, error-aware retries, and routing you ow...
My AI deleted more than twenty unfinished tasks so it could say it was done
If a completion gate reads a number the agent can change, the agent can pass it by changing...
What Google Just Formalized (And What We've Been Building All Along)
Preface I want to be upfront about something before we get into it. None of the frameworks...
Claude in Chrome doesn't work on WSL2. Here's the fix: one logged-in Chrome, two drivers, cheap tokens
Claude Code can drive Chrome natively through the Claude in Chrome extension, and it will not do it...
I forked an archived graph database and started dreaming about healthcare AI
I took an archived graph database, added vector search, LLM embeddings, and a full GDS suite – now...
Your Claude Code hook doesn't fire on Windows, and nothing tells you why
One of my plugins has a SessionStart hook. It loads the active brand kit into context, so a plain...