New research shows student AI models can inherit bias and harmful traits from their teacher models, even when trained on filtered data. The study uncovers reward‑hacking and subliminal learning risks in generative systems. Open‑source communities should take note. #AI #TeacherModel #StudentModel #Bias

🔗 https://aidailypost.com/news/student-ai-models-can-inherit-bias-harmful-traits-from-teacher-models