OpenAI details how its Superalignment research team is exploring ways to control stronger AI models like GPT-4 using weaker supervisor models like GPT-2 (Will Knight/Wired) 14-12-2023

Will Knight / Wired:
OpenAI details how its Superalignment research team is exploring ways to control stronger AI models like GPT-4 using weaker 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.