Back to Home

#AI

6 articles

AI Thoughts

What Spec-Driven Development Gets Wrong

And How to Fix It

Spec-driven development fails for the same reason all documentation-first initiatives fail: maintenance falls entirely on humans. Augment Code's Intent changes that by making both humans and agents responsible for keeping the spec honest.

AI Thoughts

The File System Is the New Database

How I Built a Personal OS for AI Agents

A deep dive into Personal Brain OS — a Git-based file system that gives AI assistants persistent context, voice, memory, and relationships. Why context engineering beats prompt engineering.

AI Thoughts Featured

The Invisible Walls That Let AI Run Free

A Global Survey of Sandbox Technology and Regulation

From gVisor to Firecracker, from the EU AI Act to Singapore's GenA.I. Sandbox — how the race to contain autonomous AI agents is reshaping the infrastructure of intelligence itself.

AI Thoughts

When AI Learns to Have a Conversation

Inside NotebookLM's Audio Overview

How Google's NotebookLM turns documents into realistic podcast conversations — and what it reveals about the future of how we absorb information.

AI Thoughts Featured

LLMs Are Not Just Models

They're the New Operating System

Distilling Andrej Karpathy's framework — dual-file architecture, three-stage training, System 1/2 cognition, and the LLM-as-OS thesis — into a technical argument about where large language models are heading.

AI Thoughts

Building AI Products People Actually Love

Lessons from Granola

How Granola's philosophy of restraint, radical simplicity, and augmentation over replacement created a meeting tool users call life-changing.