AI Safety Research Mission Statement
Conner Leahy and Beff Jezos Debate
The Big Debate: Two Divergent Views
MAX TEGMARK and YANN LECUN
Exploring Divergent Views on AI Safety:
What is in the EU AI ACT?
For Artificial Intelligence
A Framework for U.S. AI Governance: Creating a Safe and Thriving AI Sector Dan Huttenlocher Asu Ozdaglar David Goldston
This technique already used extensively
Mechanistic Interpretability is explained
The Paradigm shift we need NOW!
AI imperative of Robust design
"The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation" (2022) by the National Academies of Sciences
"AI Safety: The Search for Robust Artificial Intelligence" (2021) by Stuart Russell and Peter Norvig.
"Robust Artificial Intelligence: The Key to Ensuring the Safety and Reliability of AI Systems" (2020) by Dario Amodei et al.