AI & Cognition
Page 4 of 4.
Codebases as External First Brains
To understand a large codebase, don't read it; build a mental model. A codebase is an externalized knowledge graph, and understanding it means rebuilding it in your head.
Debugging the First Brain: Logic Building in Programming
Logic building is not syntax; it is an accurate mental model of the system. A bug is a broken edge in that model, and offloading code to AI quietly stops you building it.
How to Manage Autonomous AI Agents: Verify the Swarm
How to manage autonomous AI agents? You become the verifier. Hallucinations compound across a swarm, so you can only run as many agents as you can check.
How to Build a Company Brain (the Enterprise Exocortex)
How to build a company brain? An enterprise knowledge graph structures the explicit layer, but most projects fail for lack of graph-thinking people.
Do Large Language Models Understand Language?
LLMs produce fluent, useful language without anything most people would call understanding. Pulling those two facts apart tells us something about language itself.
How Large Language Models Work, in Plain English
No math, no jargon. A clear explanation of what a large language model is doing when it writes, why it works at all, and where it breaks.