-
Why “More Training” Didn’t Fix the Undertrained Tool — a Deeper Diagnosis (Ep:06.07)
Oversampling a tool’s training data 4x more didn’t fix it — because the real problem wasn’t repetition count, it was the size of the tool’s input domain relative to what…
-
Loss Masking, Properly Tested: Why the First Experiment Failed and the Second One Worked (Ep:05.06)
A properly designed experiment — more data, a task requiring genuine rule-learning, a real held-out test set — finally shows loss masking’s real benefit clearly, and reveals a precise mechanistic…
-
Is Your AI Agent Actually Intelligent, or Just a Very Good Parrot?
Every AI agent demo looks intelligent. That’s the problem. A demo is, almost by definition, a curated set of inputs the builder already knows the system handles well. The interesting…
-
What Is Intelligence, Really? (From Zero to Agents, Episode 00.01)
Last episode ended with a question. Here’s a definition worth pressure-testing (a very common first instinct — someone may say): “A system is intelligent if it can analyze requirements and…
