research
∙
06/19/2022
Modeling Transformative AI Risks (MTAIR) Project – Summary Report
This report outlines work by the Modeling Transformative AI Risk (MTAIR)...
share
research
∙
01/09/2022
Arguments about Highly Reliable Agent Designs as a Useful Path to Artificial Intelligence Safety
Several different approaches exist for ensuring the safety of future Tra...
research
∙
08/04/2020
Forecasting AI Progress: A Research Agenda
Forecasting AI progress is essential to reducing uncertainty in order to...
research
∙
11/22/2018
Oversight of Unsafe Systems via Dynamic Safety Envelopes
This paper reviews the reasons that Human-in-the-Loop is both critical f...
research
∙
10/16/2018
Multiparty Dynamics and Failure Modes for Machine Learning and Artificial Intelligence
Overoptimization failures in machine learning and artificial intelligenc...
research
∙
10/16/2018
Overoptimization Failures and Specification Gaming in Multi-agent Systems
Overoptimization failures in machine learning and AI can involve specifi...
research
∙
03/13/2018