Anthropic:

Anthropic details using AI agents to accelerate alignment research on “weak-to-strong supervision”, where a weak model supervises the training of a stronger one  —  Large language models' ever-accelerating rate of improvement raises two particularly important questions for alignment research.

Anthropic:

Anthropic details using AI agents to accelerate alignment research on “weak-to-strong supervision”, where a weak model supervises the training of a stronger one  —  Large language models' ever-accelerating rate of improvement raises two particularly important questions for alignment research.

Source: TechMeme
Source Link: http://www.techmeme.com/260414/p43#a260414p43