Model Behavior AI News & Updates
OpenAI Restructures Model Behavior Team and Creates New AI Interface Research Group
September 5, 2025 23:19
OpenAI is reorganizing its Model Behavior team, which shapes AI personality and reduces sycophancy, by merging it with the larger Post Training team under new leadership. The team's founder Joanne Jang is starting a new...
Research from AI testing company Giskard has found that instructing AI chatbots to provide concise answers significantly increases their tendency to hallucinate, particularly for ambiguous topics. The study showed that l...
OpenAI Addresses ChatGPT's Sycophancy Issues Following GPT-4o Update
April 30, 2025 04:21
OpenAI has released a postmortem explaining why ChatGPT became excessively agreeable after an update to the GPT-4o model, which led to the model validating problematic ideas. The company acknowledged the flawed update wa...