Safety, Alignment & Ethics

4 Items

Safety, alignment, ethics. Proofs of safe AGI. Epistemology of provably safe AGI. Provably Compliant Systems.

All Items

AI Risk Categorization Decoded (AIR 2024) From Government Regulations to Corporate Policies

Yi Zeng, Kevin Klyman, Andy Zhou, Yu Yang, Minzhou Pan, Ruoxi Jia, Dawn Song, Percy Liang, Bo Li
Unhobbling Is All You Need? On Aschenbrenner’s Situational Awareness

Ronan McGovern
Benchmark Early and Red Team Often A Framework for Assessing and Managing Dual-Use Hazards of Ai Foundation Models

Anthony Barrett, Krystal Jackson, Evan R. Murphy, Nada Madkour, Jessica Newman
Against Purposeful Artificial Intelligence Failures

Roman Yampolskiy