AI Research1 min reading time

Value generalisation Theory of Change: putting it into practice

Alignment Forum
Read the full article
The article discusses the practical application of the Value Generalisation Theory of Change, a framework aimed at improving AI alignment by ensuring AI systems generalize human values effectively.

More on this story


More in AI Research

AI Research1 min read

Different eval awareness may track different graders

LessWrong
AI Research1 min read

Tracing Subliminal Learning Through Pretraining

LessWrong
AI Research13 min read

What Is Data Poisoning? How Attackers Corrupt AI Models and Datasets

Unite.AI