It should deal with the problem of managing “super-intelligent” artificial intelligence systems. A post by Jan Leike, Sutzkever and head of the “consistency group” at OpenAI, noted that artificial intelligence superior to human intelligence could emerge in the coming years.
They emphasize the need to explore ways to control and limit such systems to ensure they are safe and ethical.
The Superalignment team will have access to OpenAI’s key computing resources and will work to solve the technical challenges of managing superintelligent AI over the next four years.
One of the team’s primary goals will be to develop an “automated human-level consistency explorer” that will train AI to evaluate other AI systems and conduct consistency research.
OpenAI suggests that AI can handle this task more efficiently and productively than humans.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
