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 (Will Knight/Wired)

December 14, 2023

3

[ad_1]

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.

[ad_2]

Source link

Previous article

“everything will be decided in the coming days”, according to political scientist Jérôme Fourquet

Next article

A first climate trial against the Government of Canada

Latest