no code implementations • 19 Jun 2022 • Sam Clarke, Ben Cottier, Aryeh Englander, Daniel Eth, David Manheim, Samuel Dylan Martin, Issa Rice
This report outlines work by the Modeling Transformative AI Risk (MTAIR) project, an attempt to map out the key hypotheses, uncertainties, and disagreements in debates about catastrophic risks from advanced AI, and the relationships between them.
no code implementations • 26 Apr 2022 • Halie M. Rando, Christian Brueffer, Ronan Lordan, Anna Ada Dattoli, David Manheim, Jesse G. Meyer, Ariel I. Mundo, Dimitri Perrin, David Mai, Nils Wellhausen, COVID-19 Review Consortium, Anthony Gitter, Casey S. Greene
These two categories of tests provide different perspectives valuable to understanding the spread of SARS-CoV-2.
no code implementations • 9 Jan 2022 • Issa Rice, David Manheim
Several different approaches exist for ensuring the safety of future Transformative Artificial Intelligence (TAI) or Artificial Superintelligence (ASI) systems, and proponents of different approaches have made different and debated claims about the importance or usefulness of their work in the near term, and for future systems.
no code implementations • 3 Nov 2021 • William Waites, Matteo Cavaliere, Vincent Danos, Ruchira Datta, Rosalind M. Eggo, Timothy B. Hallett, David Manheim, Jasmina Panovska-Griffiths, Timothy W. Russell, Veronika I. Zarnitsyna
Transmission models for infectious diseases are typically formulated in terms of dynamics between individuals or groups with processes such as disease progression or recovery for each individual captured phenomenologically, without reference to underlying biological processes.
no code implementations • 4 Aug 2020 • Ross Gruetzemacher, Florian Dorner, Niko Bernaola-Alvarez, Charlie Giattino, David Manheim
This paper describes the development of a research agenda for forecasting AI progress which utilized the Delphi technique to elicit and aggregate experts' opinions on what questions and methods to prioritize.
no code implementations • 22 Jun 2020 • William Waites, Matteo Cavaliere, David Manheim, Jasmina Panovska-Griffiths, Vincent Danos
This paper gives an introduction to rule-based modelling applied to topics in infectious diseases.
no code implementations • 22 Nov 2018 • David Manheim
This paper reviews the reasons that Human-in-the-Loop is both critical for preventing widely-understood failure modes for machine learning, and not a practical solution.
no code implementations • 16 Oct 2018 • David Manheim
An important challenge for safety in machine learning and artificial intelligence systems is a~set of related failures involving specification gaming, reward hacking, fragility to distributional shifts, and Goodhart's or Campbell's law.
no code implementations • 13 Mar 2018 • David Manheim, Scott Garrabrant
There are several distinct failure modes for overoptimization of systems on the basis of metrics.