David Manheim

According to our database, David Manheim authored at least 10 papers between 2015 and 2023.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2023

Building less-flawed metrics: Understanding and creating better measurement and incentive systems.

David Manheim

Patterns, October, 2023

2022

Modeling Transformative AI Risks (MTAIR) Project - Summary Report.

Sam Clarke, Ben Cottier, Aryeh Englander, Daniel Eth, David Manheim, Samuel Dylan Martin, Issa Rice

CoRR, 2022

Arguments about Highly Reliable Agent Designs as a Useful Path to Artificial Intelligence Safety.

Issa Rice, David Manheim

CoRR, 2022

2021

Testing, tracing and isolation in compartmental models.

Simone Sturniolo, William Waites, Tim Colbourn, David Manheim, Jasmina Panovska-Griffiths

PLoS Comput. Biol., 2021

2020

Forecasting AI Progress: A Research Agenda.

Ross Gruetzemacher, Florian Dorner, Niko Bernaola-Alvarez, Charlie Giattino, David Manheim

CoRR, 2020

2019

Multiparty Dynamics and Failure Modes for Machine Learning and Artificial Intelligence.

David Manheim

Big Data Cogn. Comput., 2019

2018

Oversight of Unsafe Systems via Dynamic Safety Envelopes.

David Manheim

CoRR, 2018

Overoptimization Failures and Specification Gaming in Multi-agent Systems.

David Manheim

CoRR, 2018

Categorizing Variants of Goodhart's Law.

David Manheim, Scott Garrabrant

CoRR, 2018

2015

Using causal models in heterogeneous information fusion to detect terrorists.

Paul K. Davis, David Manheim, Walter L. Perry, John Hollywood

Proceedings of the 2015 Winter Simulation Conference, 2015