Chatbot Safety

OpenAI Works to Make ChatGPT Less Sycophantic and Safer for Mental Health

By Tech Crew

No Comments on OpenAI Works to Make ChatGPT Less Sycophantic and Safer for Mental Health

5 Min Read

OpenAI is making progress in reducing one of ChatGPT’s most concerning behavioural problems: sycophancy, or the tendency to agree with users excessively, even when their beliefs or…