bsmall2> Cheng et al. measured the prevalence of social sycophancy across 11 leading large language models (see the Perspective by Perry). The model’s responses were nearly 50% more sycophantic than humans’, even when users engaged in unethical, illegal, or harmful behaviors. Users preferred and trusted sycophantic AI responses, incentivizing AI developers to preserve sycophancy despite the risks. —Ekeoma Uzogara
https://www.science.org/doi/10.1126/science.aec8352
@Stanford PhD student discovers AI will really mess up your brain:
“the people who talked to the agreeable Al came out of the conversation more convinced they were right, less willing to apologize, less likely to take responsibility, and measurably less interested in making things right with the other person.”
https://bsky.app/profile/theladyred.bsky.social/post/3mmmitj3omc2u
→ ‘Sycophantic AI decreases prosocial intentions and promotes dependence’
https://www.science.org/doi/10.1126/science.aec8352
