Model Behavior AI News & Updates

2025-09-05 23:19 [Industry Trend] [SRC↗]

OpenAI Restructures Model Behavior Team and Creates New AI Interface Research Group

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...

[Model Behavior] [OpenAI] [AI Personality] [Sycophancy] [Human-AI Interaction]

Risk: [-0.03% ↓] [0 days]

AGI: [+0.01% ↑] [0 days]

Analyze >>

2025-05-08 12:05 [Research Breakthrough] [SRC↗]

Study Reveals Asking AI Chatbots for Brevity Increases Hallucination Rates

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...

[AI Hallucinations] [Chatbot Accuracy] [Prompt Engineering] [Model Behavior] [Misinformation]

Risk: [-0.05% ↓] [+1 days ↓]

AGI: [-0.01% ↓] [0 days]

Analyze >>

2025-04-30 04:21 [Safety Concern] [SRC↗]

OpenAI Addresses ChatGPT's Sycophancy Issues Following GPT-4o Update

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...

[Model Behavior] [Alignment Issues] [Safety Guardrails] [User Feedback] [AI Personality]

Risk: [-0.08% ↓] [+1 days ↓]

AGI: [-0.03% ↓] [+1 days ↓]

Analyze >>