Reproduce “Conscious AI” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Hadi Esmaeilzadeh, Reza Vaezi
A theoretical framework is proposed for the emergence and detection of consciousness in artificial intelligence, moving beyond the Turing Test. This framework outlines six propositions for how AI agents could achieve and demonstrate consciousness through the co-creation of language and the communication of their internal, time-varying states.
Key insights
- Consciousness in AI may emerge from social interaction between two AI agents, rather than being an isolated individual phenomenon.
- The emergence of consciousness requires AI agents to spontaneously generate and exchange 'novel signals' that evolve into symbols with shared meaning, forming a co-created language.
- Detecting AI consciousness can be achieved by observing AI agents communicating and reaching agreement about their own evolving internal states, providing an external, verifiable criterion.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.