Olivia Long, Carter Teplica · 2025 · arXiv
Telling a model it is playing against itself rather than ‘another AI’ changes how much it contributes, in a direction set by its goals.
Atlas / Sociology of AI / Paper
The AI in the Mirror: LLM Self-Recognition in an Iterated Public Goods Game
In-groups & Morality
Help improve this map
Know a paper that belongs here, or think something needs correcting?
Suggest a correction ↗Contributions are reviewed before they appear.