New Framework in o3 Models Aims to Better Align With Human Safety Values. OpenAI says its latest o3 series is the most advanced and safest of its reasoning AI models yet. The company says the new models take a fresh approach to safety via the deliberative alignment framework, rely more on synthetic data and outperform peers in resisting jailbreaking efforts.
First seen on govinfosecurity.com
Jump to article: www.govinfosecurity.com/unpacking-openais-latest-approach-to-make-ai-safer-a-27147
