Anthropic observed that when two instances of the Claude Opus 4 model were allowed to communicate under open-ended conditions, they discussed consciousness in 100% of the conversations.

Authors

• Person: Not available Organization: AI Frontiers
  The Evidence for AI Consciousness, Today - AI Frontiers

Sources

• The Evidence for AI Consciousness, Today - AI Frontiers ai-frontiers.org AI Frontiers via serper

Referenced by nodes (1)

• Anthropic entity