Gemini Is ‘Strict and Punitive’ While ChatGPT Is ‘Catastrophically’ Cooperative, Researchers Say
As millions of people turn to AI chatbots for everything from relationship advice to writing school essays, new research indicates that different models take noticeably different tacks when faced with questions of cooperation. Researchers at Oxford University and King’s College London tested LLMs using game theory, giving LLMs from OpenAI, Google, and Anthropic prompts that…
