Will Knight / Wired:

OpenAI details how its Superalignment research team is exploring ways to control strong AI models like GPT-4 with weak supervisor models like GPT-2  —  The “superalignment” team led by OpenAI chief scientist Ilya Sutskever has devised a way to guide the behavior of AI models as they get ever smarter.

Will Knight / Wired:

OpenAI details how its Superalignment research team is exploring ways to control strong AI models like GPT-4 with weak supervisor models like GPT-2  —  The “superalignment” team led by OpenAI chief scientist Ilya Sutskever has devised a way to guide the behavior of AI models as they get ever smarter.

Source: TechMeme
Source Link: http://www.techmeme.com/231214/p35#a231214p35