After GPT-4o backlash, researchers benchmark models on moral endorsement—Find sycophancy persists across the board

Leave a Comment / AI, AI & Machine Learning, ai sycophancy, AI, ML and Deep Learning, Claude 3.7 Sonnet, Gemini 1.5, Global News, gpt-4o, LLaMA, llama 3, llama 4, Mistral 7B, Mistral Small, sycophancy /

Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More Last month, OpenAI rolled back some updates to GPT-4o after several users, including former OpenAI CEO Emmet Shear and Hugging Face chief executive Clement Delangue said the model overly flattered users.  The flattery, called sycophancy, often […]

After GPT-4o backlash, researchers benchmark models on moral endorsement—Find sycophancy persists across the board Read More »