Models & Researchgenerative aiai safetyresearch
Researchers Propose Framework To Make Generative AI Safer
6.8
Kookmin Univ. and UBC researchers offer a new framework to make generative artificial intelligence safer. The framework responds to the fact that generative AI's ability to create vivid images and videos has often outpaced the ability to control them, aiming to strengthen controls and reduce misuse.
Key Points
- 1Researchers propose a structured framework to improve safety controls for generative image and video models.
- 2Generative image and video generation capacity has advanced faster than mechanisms to restrict misuse or errors.
- 3The framework could guide developers and policymakers to reduce harmful outputs and strengthen model governance.
Scoring Rationale
University research proposing a safety framework is notable for practitioners and governance, but it is not a paradigm-shifting industry event.
Practice interview problems based on real data
1,625 SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems
