Most AI is built for everyone. This is built for someone.
AI systems organized around one person's evolving context: their memory, taste, preferences, rituals, aspirations, and intellectual trajectory.
Personal Intelligence is my research and creative program exploring AI systems organized around one person's evolving context: their memory, taste, preferences, rituals, aspirations, and intellectual trajectory.
The dominant paradigm optimizes for the average user across a population. I'm interested in the opposite end: systems that get sharper the longer they sit with a single person, that model not what people in general like but how this person's judgment is formed and where it's heading.
How do humans develop taste, and how can AI help us remember, refine, and act on it?
Six threads of a single context. The program is organized less around technologies than around the facets of a person these systems try to hold.
Memory
What a system should hold onto, and what it should let fade. Context that accumulates without becoming clutter.
Taste
How preference becomes discernment: the slow formation of why we like what we like, and whether a system can learn its shape.
Preferences
The stated and the revealed. Reconciling what we say we want with what we keep reaching for.
Rituals
The small, repeated acts that structure a life: the pour-over, the morning read, the way we return to things.
Aspirations
Who we are trying to become. Systems that hold the gap between the current self and the intended one.
Intellectual Trajectory
The arc of what we think about over years. Where attention has traveled, and where it is heading next.
Where the program becomes something you can use. Each takes one thread and builds a working system around it, applied to my own books, my own videos, my own coffee.