18 Sep 2026
Why evaluation is the hard part of applied AI
The model is rarely the bottleneckMost projects fail on evaluation, not architecture.Define the decision firstBuild the test set before the model
Artificial Intelligence · 10 Sep 2026
Evaluation Sets That Lie to You
A held-out set is only held out if it was separated before you started making decisions. Usually it was not.
Artificial Intelligence · 1 Sep 2026
Retrieval Is Mostly Chunking
Swapping embedding models buys you a little. Getting chunking right buys you a lot. The attention goes the wrong way round.