Eval-Driven Development
AI systems don’t fail because they’re dumb, they fail because we never define “good.”
AI systems don’t fail because they’re dumb, they fail because we never define “good.”
The topic was on evals, something that’s come up again and again in conversations with founders building AI products lately.
The three levers for steering pre-trained models and the evals that guide them.
When answers replace clicks, publishers, brands, and platforms face a new incentive structure.
Every week I see pitches that follow a similar pattern: “X for Y, powered by AI.” I call this promptware.
How Big Tech is gutting AI startups without actually buying them.