AI Research1 min reading time

Value Generalisation 3: Pre-aligned AIs

Covered by 2 sources
Read the full article
The article discusses the concept of pre-aligned AIs in the context of value generalisation, exploring how AI systems can be designed to inherently align with human values before deployment.

Covered by 2 sources


More in AI Research

AI Research5 min read

Scientists overcome a hidden obstacle to more powerful quantum computers

Science Daily
AI Research1 min read

Different eval awareness may track different graders

LessWrong
AI Research1 min read

Tracing Subliminal Learning Through Pretraining

LessWrong