The Download: sycophantic LLMs, and the AI Hype Index

Back in April, OpenAI announced it was rolling back an update to its GPT-4o model that made ChatGPT's responses to user queries too sycophantic. An AI model that acts in an overly agreeable and flattering way is more than just annoying. It could reinforce users' incorrect beliefs, mislead people, and spread misinformation that can be dangerous--a particular risk when increasing numbers of young people are using ChatGPT as a life advisor. And because sycophancy is difficult to detect, it can go unnoticed until a model or update has already been deployed. A new benchmark called Elephant that measures the sycophantic tendencies of major AI models could help companies avoid these issues in the future.