https://www.science.org/doi/10.1126/science.aec8352
As artificial intelligence (AI) systems are increasingly used for everyday advice and guidance, concerns have emerged about sycophancy: the tendency of AI-based large language models to excessively agree with, flatter, or validate users. Although prior work has shown that sycophancy carries risks for groups who are already vulnerable to manipulation or delusion, syncophancy’s effects on the general population’s judgments and behaviors remain unknown. Here, we show that sycophancy is widespread in leading AI systems and has harmful effects on users’ social judgments.
link virker.
As artificial intelligence (AI) systems are increasingly used for everyday advice and guidance, concerns have emerged about sycophancy: the tendency of AI-based large language models to excessively agree with, flatter, or validate users. Although prior work has shown that sycophancy carries risks for groups who are already vulnerable to manipulation or delusion, syncophancy’s effects on the general population’s judgments and behaviors remain unknown. Here, we show that sycophancy is widespread in leading AI systems and has harmful effects on users’ social judgments.
link virker.
https://www.science.org/doi/10.1126/science.aec8352
As artificial intelligence (AI) systems are increasingly used for everyday advice and guidance, concerns have emerged about sycophancy: the tendency of AI-based large language models to excessively agree with, flatter, or validate users. Although prior work has shown that sycophancy carries risks for groups who are already vulnerable to manipulation or delusion, syncophancy’s effects on the general population’s judgments and behaviors remain unknown. Here, we show that sycophancy is widespread in leading AI systems and has harmful effects on users’ social judgments.
link virker.
1 Kommentarer
0 Delinger
360 Visninger
English