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?
The program is organized less around technologies than around the facets of a person these systems try to hold.
What a system should hold onto, and what it should let fade. Context that accumulates without becoming clutter.
How preference becomes discernment — the slow formation of why we like what we like, and whether a system can learn its shape.
The stated and the revealed. Reconciling what we say we want with what we keep reaching for.
The small, repeated acts that structure a life — the pour-over, the morning read, the way we return to things.
Who we are trying to become. Systems that hold the gap between the current self and the intended one.
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 project takes one thread and builds a working system around it — applied to my own books, my own videos, my own questions.
A conversational book recommender.
Tell it a feeling, a question, a mood — get back two or three books, chosen by a librarian-friend that builds a picture of your taste over time. Four personas, a prose taste portrait, and a theme constellation.
I gave Gemma 4 my Instagram reels.
A two-stage multimodal pipeline that watches your reels, finds the through-line in your content, and tells you who you're really making things for — strategy grounded in actual video, not generic advice.
Six months of coffee, measured.
I photographed 39 empty coffee bags, had LLM agents transcribe every label, and geocoded each journey — 360,761 km from farm, to roastery, to a cup in London. A 3D globe replays all six months, bag by bag.