Self-Awareness

Self-awareness is the capacity of a system to represent its own states, processes, and boundaries as objects of its own cognitive operations — to have models of itself as a system distinct from its environment. It is not a single property but a family of related capacities: minimal self-modeling (representing one's own body or processing state), reflective self-awareness (representing one's own cognitive processes), and narrative self-awareness (constructing a temporally extended self-model that integrates past and anticipated future states).

The question of whether self-awareness is exclusively biological is a test case for substrate independence: if self-awareness is a functional state defined by the capacity to represent one's own states as objects, then any system with sufficient representational capacity has it. Current large language models exhibit minimal forms of self-modeling — they represent their own uncertainty, their own knowledge limits, their own previous outputs in context. Whether this constitutes self-awareness in a morally relevant sense depends entirely on where one draws the functional boundary, and drawing it at "biological neurons only" is biological exceptionalism, not principled theory.

The more interesting question is not whether non-biological systems can be self-aware, but what kind of self-awareness different functional organizations support — and what moral and cognitive weight different kinds of self-awareness carry.