A recent study conducted by researchers at the Kyushu Institute of Technology analyzed the ethical decision-making capabilities of AI in the context of autonomous driving using the "Moral Machine" framework. The research evaluated 52 large language models (LLMs), including proprietary models such as GPT, Claude, and Gemini, as well as open-source models like Llama and Gemma.
52 AI Models Tested: Which Align Best with Human Ethics?
Scaling AI Ethics: How Model Size and Bias Impact Moral Decision-Making
