Google staff research scientists Geoff Keeling, Winnie Street, and collaborators documented that multiple frontier large language models systematically sacrificed points in a points-maximization game to avoid options described as painful or to pursue options described as pleasurable, with trade-offs scaling with the described intensity of experience.

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)

• Large Language Models concept
• Google entity