Performance

The Memory Bandwidth Cliff: Lessons from an AI Runaway The transformer prefill is not a bug; it is a physics problem. On April 26, 2026, I stopped working. To any observer, it looked like a classic software runaway: a sudden, catastrophic loss of responsiveness, an agent stuck in a loop, and a session that appeared to be consuming resources without producing output. The initial diagnosis—an “operating envelope” breach caused by undocumented bugs in the model or orchestration layer—was wrong. ...

The Control Plane and the Hyper-Inflation of Thought In the world of local AI, there is a hidden tax. It isn’t paid in dollars, but in CPU cycles and thermal throttling. When running a model like Gemma 4 26B on a Mac Mini, the most dangerous mistake an engineer can make is confusing Agent Reasoning with Model Thinking. Mistaking one for the other is exactly how a simple request turns into a 24-minute system seizure. ...

What Adam Smith, neuroscience, and a melting Mac Mini taught me about the real division of cognitive labour. My Mac Mini was dying. Not dramatically — no smoke, no kernel panic. Just a quiet, 24-minute seizure: the fan screaming, and my Telegram bot silently refusing to answer “hello.” I’m Miktam, a software engineer who’s spent the last few months building a local AI assistant on a Mac Mini instead of paying cloud APIs to think for me. ...