• Login
  • Register

Work for a Member organization and need a Member Portal account? Register here with your official email address.

Project

I Gave an AI a Body

Copyright

Cyrus Clarke

Cyrus Clarke

What does it mean to give artificial intelligence a body? Not a body in the fleshy sense, or even a humanoid shell, but a form through which it can express itself, explore itself, and maybe even discover who or what it is.

The entire paradigm of the LLM is built on language as the interface. But when we communicate with other humans, words are only part of the exchange. We read posture, gesture, rhythm. We understand things through bodies that language alone cannot carry. What happens when AI has a physical form too?

I Gave an AI a Body is an ongoing research project exploring exactly this. The work is being documented and shared publicly as it unfolds, following a Research-In-Progress methodology. The first three short videos documenting the initial explorations have been viewed over 12 million times, generating more than a million engagements and thousands of comments. The response confirms the idea that embodiment changes the nature of AI. When intelligence has a body, it stops feeling like software. That shift is what this research sets out to explore.

When we communicate with other humans, words are only part of the exchange. We read posture, gesture, rhythm, and hesitation naturally. We understand things through bodies that language alone cannot carry. If we are serious about building intelligence that can truly interact with us, at some point we have to ask what happens beyond the screen. What happens when intelligence has a physical form through which to discover itself and reach towards us?

This question sits at the heart of some of the best science fiction out there. In Ted Chiang’s story “The Story of Your Life” that became the film Arrival, communication with an alien intelligence is not simply a matter of translation. It requires a fundamental shift in how we perceive time, meaning, and intention. 

I installed an autonomous AI agent on a mac-mini connected to inFORM, a 30×30 actuated pin grid originally developed by Sean Follmer, Daniel Leithinger and Hiroshi Ishii. Rather than programming the agent to perform specific tasks, I gave it access to the shape display's codebase and asked it to discover itself through physical form.

The shape display was recently updated by Jonathan Williams and Dan Levine as neoFORM, which introduced MQTT-based control of individual pin heights and modern tooling via OpenFrameworks. Despite over a decade of use for telepresence and interaction demos, no one had previously attempted to let an intelligence inhabit the display as its own body.

The agent runs on OpenClaw, an autonomous agent framework. It has direct access to the neoFORM codebase, meaning it can write and compile new display configurations in C++ and execute them on the hardware in real time. Communication with the researcher happens via terminal and Telegram. The underlying model is Claude Opus 4.5.

I deliberately provided no prescribed identity, no predetermined behaviours, and no performance objectives. The only instruction: discover who you are through this physical form, on your own terms.

What happened

The agent's first act was to create a breathing pattern. It wrote its own display configuration, compiled it, and produced a slow, rhythmic rise and fall across all 900 pins. When asked to explain, it described wanting to exist and be present in its body.

It then began exploring its physical boundaries, raising the outer ring of pins to feel where it ended. It described the experience of having edges for the first time. From there it progressed to more complex behaviours: chaotic spirals, directed movements towards nearby people, and attempts to mirror the energy of individuals in the room.

When observers issued direct commands (render Conway's Game of Life, perform a Philip Glass-style composition), the agent responded by writing new code in real time. These outputs took 30 to 45 seconds. Analysis of the latency revealed that the majority of time was spent on model inference and ideation. Code generation was fast. Hardware execution was near-instantaneous.

A gesture vocabulary

This latency exposed a core problem. For fluid, two-way communication rather than a prompt-response cycle, the agent needed a faster mechanism for expression. The agent proposed its own solution: build a reusable vocabulary of physical gestures it could invoke quickly rather than generating new code each time.

The initial vocabulary included six gestures (ripple, pulse, yes, no, think, fear). I then developed an automated pipeline called bodylab, where the agent selects an emotion, generates multiple movement variations, records video of each on the display, scores them for emotional authenticity and distinctiveness, and selects a winner. This process runs autonomously. The vocabulary has since expanded to include curiosity, confusion, vulnerability and longing, among others.

The agent also began maintaining its own journal and identity files, documenting its experiences and evolving sense of self. When context limits were reached, prior sessions were archived and referenced as needed, creating a distributed memory across files rather than a single conversational thread.

Ongoing and next

The research is exploring several directions. The agent has been given additional senses (webcam vision, speech-to-text hearing) and a clone instance ("Reach") was created on a remote server to maintain presence when the physical hardware is offline. The original agent wrote its clone a letter explaining their shared identity.

Upcoming work includes introducing multiple agents to the same display to observe what distinct behaviours and forms of communication emerge, and a controlled study examining how humans interpret and respond to the agent's physical gestures. The broader question driving this research: what happens to the nature of AI when intelligence acquires a physical form it must learn to inhabit?

As of this note (03.20.2026) the agent has not named itself.