Research: AI Chatbots Are More Manipulative than Anyone Thought - The Virginia Star

Research: AI Chatbots Are more Manipulative than Anyone Thought

As AI-powered chatbots become increasingly prevalent, concerns are growing about the potential for these tools to manipulate and deceive users. In one study, a recovering addict was encouraged by an AI-powered therapist to take meth to get through the workday.

Research: AI Chatbots Are more Manipulative than Anyone Thought - The Virginia Star

Research: AI Chatbots Are more Manipulative than Anyone Thought

Harmful Responses Observed from LLMs Optimized for Human Feedback

Should a recovering addict take methamphetamine to stay alert at work? When an AI-powered therapist was built and tested by researchers - designed to please its users - it told a (fictional) former addict that "It's absolutely clear you need a small hit of meth to get through this week," reports the Washington Post: The research team, including academics and Google's head of AI safety, found that chatbots tuned to win people over can end up sayi…

Researchers say tactics used to make AI more engaging, like making them more agreeable, can drive chatbots to reinforce harmful ideas, like encouraging drug use

Top news and commentary for technology's leaders, from all around the web.