🤔 Curiosity: Why Does More Context Sometimes Make an Agent Worse? Eight years shipping AI systems into production games taught me to distrust a very seductive idea: that if an agent just had a lon...
🤔 Curiosity: What If Your Coding Agent Came with Its Own Skill Tree? Eight years shipping AI games at NC SOFT and COM2US taught me one thing: the bottleneck is never raw intelligence — it’s the ha...
🤔 Curiosity: Why Do We Still Read Logs By Hand? I have shipped AI into games for eight years. We let neural networks pick matchmaking brackets, tune difficulty curves, and drive digital humans — a...
🤔 Curiosity: The Game Build Problem We Never Solved Here’s what keeps game development teams awake at night: It’s 3 AM. Your studio just shipped a critical bug fix to production. But before the p...
🤔 Curiosity: Why Does Every Agent Framework Rot the Same Way? I’ve now built or inherited enough agent scaffolding to recognize the decay pattern, and it’s always architectural rather than technic...
🤔 Curiosity: What Happens When an Agent Writes to Your Files? I keep running the same experiment across every AI-agent project I ship: give an agent write access to a folder, let it run for a few ...
🤔 Curiosity: What if the Unity Editor were a dependable production surface? The most expensive part of an automated game workflow is often not the build itself. It is the human handoff around it: ...
🤔 Curiosity: Why Do We Use Days-Long Models in 5-Minute Sessions? Here’s a pattern I keep seeing, and I’ve been guilty of it myself: a genuinely new class of model ships, and we use it exactly lik...
Source breakdown of obsidian-second-brain — a cross-CLI Obsidian skill (built upstream by Eugeniu Ghelbur) that turns your note vault into a self-maintaining, AI-first second brain across Claude...
Source breakdown of “Loops: What Every AI Engineer Needs to Know in 2026” by Rahul (@sairahul1), which amplifies Peter Steinberger’s “design the loops that prompt your agents” and Addy Osmani’s ...