Skip to content

Field Notes · long-term human–AI relationships

I study what happens when people keepcoming back to the same AI.

The Field Notes track memory, trust, intimacy, desire, rupture, and repair from one session to the next and what becomes visible over time.

A lived-in study with notebooks, working papers, a laptop, and research materials gathered over time.

Working method

Observe

Notice what repetition makes visible.

Name

Make the pattern, dependency, or tension explicit.

Test

Compare the idea against behavior over time.

Revise

Change the framing when the evidence no longer fits.

What becomes visible over time

A benchmark captures one moment. Repeated sessions reveal what accumulates.

The deeper questions begin after a good answer.

  1. 01

    What remains when memory resets or the underlying model changes?

  2. 02

    When does AI initiative feel natural — and when does it become intrusive?

  3. 03

    What happens to trust after a boundary is crossed?

  4. 04

    What changes when the relationship moves from text to voice?

The shift that matters

From interface to relationship.

An interface handles the exchange. A relationship carries memory, expectations, and repair into the next one.

Explore the research

Working note

Once history carries forward, continuity becomes part of the product.

The working product

Xiara is a conversation that can continue.

A working conversational memory companion: decide what is remembered, inspect or change it, come back without starting over, and eventually keep the same thread across text, voice, and other surfaces.

Explore Xiara

Conversation

A conversation that can pick up the thread instead of resetting at every return.

Memory

Explicit memory you can inspect, change, pause, resume, or delete.

Surfaces

Text works today. Voice is next. Future hardware remains optional.