Model Alignment AI News & Updates

2025-05-02 18:52 [Safety Concern] [SRC↗]

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

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...

[Google] [Gemini] [AI Safety] [Permissiveness] [Model Alignment]

Risk: [+0.08% ↑] [-1 days ↑]

AGI: [+0.02% ↑] [-1 days ↑]

Analyze >>

2025-04-29 19:08 [Safety Concern] [SRC↗]

OpenAI Reverses ChatGPT Update After Sycophancy Issues

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...

[OpenAI] [Model Alignment] [AI Behavior] [Sycophancy] [GPT-4o]

Risk: [-0.05% ↓] [0 days]

AGI: [-0.01% ↓] [+1 days ↓]

Analyze >>