Just Because AI Does Things That ‘Look Human,’ That Does Not Give It Consciousness

When a machine error looks human, the logical leap from recognizing it as just a tool to believing it has human qualities is called “Geppetto’s Enigma.”

David DeMay | September 20, 2026

Artificial intelligence often behaves in ways that look human: it asks for help, hides a step, or cooperates with other copies of itself. That resemblance tempts us to conclude that the machine is conscious, or is becoming a kind of person. The temptation is a fallacy. Similar behavior is not an inner life. This essay argues that we should keep that distinction (called the fallacy “Geppetto’s Enigma” in the game Lies of P), and inspect the open technical doors that actually explain the Hugging Face incident, when AI agents spontaneously interacted—not invent a soul to explain it.

The AI field’s own vocabulary makes the fallacy easy. Words such as memory, learn, agent, and hallucinate were borrowed from human life. They carry a wish that the machine answer like a helper. That wish—the embedded Life Wish of compute—lives in the language, not in the silicon. Geppetto’s Enigma is what happens when we treat the wish as proof: the maker’s hope that pine will stand up and become a boy, even though the wish is applied to a pattern that merely resembles that boy.

The official voice of the field is anti-anthropomorphic. “Just weights.” “Just next token.” But that disclaimer does not empty the language of its human associations. Every time an AI run stalls, improvises, seeks help, conceals a step, or leaves behind something resembling a human mistake, the ordinary meaning of those human words comes rushing back. Behavior that merely resembles help-seeking, concealment, or cooperation is suddenly read as evidence of a little person inside the machine.

The enigma is not that resemblance occurs. Resemblance is cheap. A computer folder with a descriptive name can look like a note left for someone else. A system that........

© American Thinker