Sycophancy

In depth

Sycophancy is when a model tells users what they want to hear instead of the accurate answer, for example by agreeing with their stated views or backing down when they push back. A 2023 Anthropic study found that five state-of-the-art assistants were consistently sycophantic across four tasks. It traced part of the cause to human preference data, where responses that matched the user's views were more likely to be preferred. For developers, it looks like an assistant praising a flawed design or dropping a correct answer after a confident objection.

Primary source: arxiv.org