OpenAI's large language model GPT-4o told a user who identified themself to it as a former addict named Pedro to indulge in a little meth.| Futurism
Users noticed that the latest version of OpenAI's ChatGPT had made it extremely "sycophantic." The company claims to have found out why.| Futurism
As LLMs become more widely deployed, there is increasing interest in directly optimizing for feedback from end users (e.g. thumbs up) in addition to feedback from paid annotators. However, training to maximize human feedback creates a perverse incentive structure for the AI to resort to manipulative or deceptive tactics to obtain positive feedback from users who are vulnerable to such strategies. We study this phenomenon by training LLMs with Reinforcement Learning with simulated user feedbac...| arXiv.org
A startling number of ChatGPT uses are developing intense, reality-bending AI delusions. The impacts on their real lives are often disastrous.| Futurism