jev class of models have no generative decoder loop, have bounded outputs, utilize parallel inference, & have extreme compression/efficiency incentives. this makes them perfect to run on device (this will happen soon). at that point you can put judgment into basically every existing interaction like notifications, email, camera, keyboard, home screen, sensors, shortcuts, accessibility, etc. with zero marginal cost & it would be near instant (users would never feel the lag of an llm). more specifically you can frame lots of problems that are potentially too expensive for an llm into decisions, stuff like: should i surface this? is this unusual? does the user care? which action is appropriate? is this interruption worth it? did their intent change? should this ui adapt? this basically adds a new computational programming primitive for ~free.

truly great great conversations are more a form of exploration rather than pure information exchange. each person expands the other’s internal world rather than merely extracting.