Independent researcher Christopher Ackerman found evidence of limited but real introspective abilities in AI models by testing whether models can access and use internal confidence signals without relying on self-reports, noting these abilities grow stronger in more capable models.

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)

• AI models concept