Superalignment | search
Click here to view Superalignment news from 60+ newspapers.
Bookmark or Share- News - OpenAIStay up to speed on the rapid advancement of AI technology and the benefits it offers to humanity.
- Safety & responsibility - OpenAIA collection of resources about our safety practices across development, deployment, and the use of our models. Artificial general intelligence has the potential to benefit nearly every aspect of our lives—so it must be developed and deployed responsibly.
- Weak-to-strong generalization - OpenAIA core challenge for aligning future superhuman AI systems (superalignment) is that humans will need to supervise AI systems much smarter than them. We study a simple analogy: can small models supervise large models?
- API platform | OpenAICustomize a model’s existing knowledge and behavior for a specific task using text and images via supervised fine-tuning. Plus, use our Model Distillation tools to fine-tune smaller models on the outputs of more capable models. Learn more.
- Introducing Superalignment - OpenAIIntroducing Superalignment. We need scientific and technical breakthroughs to steer and control AI systems much smarter than us. To solve this problem within four years, we’re starting a new team, co-led by Ilya Sutskever and Jan Leike, and dedicating 20% of the compute we’ve secured to date to this effort.
More
