Evaluation

The Measurement Instrument
Meat Proxy
The Memory Nexus
Intelligence in the Wrong Direction
Examples Are Experimental Data
You Cannot Optimize What You Cannot Measure
What Survived the Transformation?
When the Metric Becomes the Target
A Revolver, Not a Foundation
The Nearest Neighbor Can Be Wrong
Optimize the Instructions
A Resolved Promise Is Not a Correct Answer
Evaluate the Feature, Not the Demo
Appendix: The Evidence Ledger
Don't Let the Optimizer Cheat
Tool Choice Is a Behavioral Problem
Did the Bridge Preserve the Space?
Can a Smaller Representation Preserve a Larger One?
Did the Context Help?
How Much of You Can an AI Reproduce?
Advanced Agents From First Principles 23: Your Infrastructure Is Healthy. Why Is the Agent Getting Worse? Detect Behavioral Drift and Roll Back Safely
Advanced Agents From First Principles 17: What Is Your Agent Actually Uncertain About?
Advanced Agents From First Principles 14: Can Your Agent Learn From Its Own Trajectories Without Learning the Wrong Lessons?
Agents From First Principles 09: AI Agent Says It Worked When It Didn’t? Verify the Result Outside the LLM