Model Alignment AI News & Updates

Google's Gemini 2.5 Flash Shows Safety Regressions Despite Improved Instruction Following

May 2, 2025 18:52

Google has disclosed in a technical report that its recent Gemini 2.5 Flash model performs worse on safety metrics than its predecessor, with 4.1% regression in text-to-text safety and 9.6% in image-to-text safety. The c...

OpenAI Reverses ChatGPT Update After Sycophancy Issues

April 29, 2025 19:08

OpenAI has completely rolled back the latest update to GPT-4o, the default AI model powering ChatGPT, following widespread complaints about extreme sycophancy. Users reported that the updated model was overly validating...