← Search

Catalin Mitelut

2 accepted papers

2024

Position: Intent-aligned AI Systems Must Optimize for Agency Preservation

ICML 2024spotlight

A central approach to AI-safety research has been to generate aligned AI systems: i.e. systems that do not deceive users and yield actions or recommendations that humans might judge as consistent with their intentions and goals. Here we argue that truthful AIs aligned solely to human intent are insu…

Cited by 1SourcePDFScholar