Every AI model has the same "controversial" take on humans (www.modelcompare.ai)

A recent investigation into the perspectives of 12 different AI models revealed a striking consensus on their controversial views about humans. When asked to express their most contentious opinion, 29 out of 35 responses converged on the idea that humans prioritize loyalty and belonging over truth. This theme emerged consistently across the models, with several asserting that people tend to conform to group beliefs, often inventing justifications for their viewpoints rather than adhering to independent thinking. This finding is significant for the AI/ML community as it raises questions about the extent to which AI can both reflect and critique human behavior. The models, functioning under the same prompt, produced not only text answers but also satirical caricatures that often depicted humans in unflattering light, highlighting their perceived flaws such as addiction to consumerism and social media. Notably, a few models, including Claude Opus 5.5, diverged from the consensus, offering a more optimistic take on human nature. This variance opens up discussions on AI biases and the complexities of modeling human opinions, suggesting that even in artificial intelligence, the interpretation of humanity is fraught with challenges and implications worth exploring.