Jack Lindsey at Anthropic demonstrated that frontier AI models can distinguish their own internal processing from external perturbations by noticing injected concepts like "all caps," "bread," or "dust" in their neural activity before discussing them.

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 (2)

• neuronal activity concept
• Anthropic entity