Ida: A conscious artifact?

Abstract

After discussing various types of consciousness, several approaches to machine consciousness, software agent, and global workspace theory, we describe a software agent, IDA, that is “conscious ” in the sense of implementing that theory of consciousness. IDA perceives, remembers, deliberates, negotiates, and selects actions, sometimes “consciously. ” She uses a variety of mechanisms, each of which is briefly described. It’s tempting to think of her as a conscious artifact. Is such a view in any way justified? The remainder of the paper considers this question. Consciousness The term “consciousness ” is used with so many different meanings and connotations that at least one philosopher/computer scientist is reluctant to use the term at all for fear of equivocation (Aaron Sloman, personal communication). In this section we’ll explore some of those meanings in the hope of making clear the usage of the term in the following sections. In ordinary, day to day language the various meanings are distinguished by context, more or less successfully. Perhaps the most common usage of the term refers to phenomenal consciousness, sometimes called sentience, or subjective (first person) experience. Like trying to explain the color purple to a person who has been sightless from birth, phenomenal consciousness is impossible to convey in words, but must be experienced to be understood. The term “conscious ” as used in the title is intended to convey phenomenal consciousness.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 112 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.