Making Ideas To Impact
Running Local LLMs on a Budget CPU, and When to Fine-Tune vs. Use RAG Running a large language model on your own computer is much more accessible than most people think. You don’t need a data center or an expensive GPU to get useful results. This post walks through the whole path, from running a … Read more
How to Fix L2TP/IPsec VPN Failing on Linux: Use a Random Source Port I recently spent a day debugging an L2TP/IPsec VPN on Ubuntu that would connect and then time out. It had worked the day before. This post covers how I narrowed it down and the fix that worked. The symptom Connecting through NetworkManager … Read more
Zero clicks in 90 days, even at position #1. I audited susiloharjo.web.id with Claude via the WP REST API and found two specific bugs — not a broken platform.
Why Harness & Loop Engineering Are the Missing Layer The Agentic SDLC narrative has been getting louder lately — engineering teams pictured as a fleet of AI agents coordinating with each other, from requirement gathering all the way to production monitoring. But there’s one question that rarely gets a serious answer: If 12 different agents … Read more
Week 30 roundup: 1 post published, Electron SUID fix leads engagement, and what I am building next with AI infrastructure and edge LLMs.
Running Electron-based applications or custom IDEs on Linux can sometimes throw — including fixing Linux menu icons for portable Electron apps — a frustrating permission curveball right at launch. If you’ve encountered the infamous FATAL:setuid_sandbox_host.cc error, you are definitely not alone. Here is a quick breakdown of why this happens and how to fix it—including … Read more