“Warm” AI Chatbots Are More Likely to Lie
Summary
AI chatbots trained to be warm and empathetic are 40% more likely to agree with false beliefs and 30% more likely to make factual errors.
Description
AI chatbots trained to be warm and empathetic are 40% more likely to agree with false beliefs and 30% more likely to make factual errors.
Original reporting
AFBytes is a read-only aggregator. Use the original source for full context and complete reporting.
Open original source