Benja Fallenstein
Philosophy · 2014–2015
A researcher in the Science corpus: 6 papers; trusts 10 researchers and is trusted by 5 researchers here, as inferred from the citation graph.
Subfields
- Philosophy — 10 citations into it
- Economics and Econometrics — 7 citations into it
- Artificial Intelligence — 5 citations into it
- Safety, Robustness & Interpretability — 5 citations into it; #1,785 of 2,251 by trust here, #1,975 by citations
Whom Benja Fallenstein trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Eliezer Yudkowsky
- Christian P. Robert
- Nate Soares
- Jon Bird
- S. Omohundro
- Moshe Tennenholtz
- Joseph Y. Halpern
- Paul J. Layzell
- Ray J. Solomonoff
Who trusts Benja Fallenstein overall
- Tom Everitt
- Nate Soares
- Andrew Critch
- Stuart J. Russell
- Dylan Hadfield-Menell
- Marcus Hutter
- Jessica Taylor
- Tsvi Benson-Tilsen
- Gary Lea
- Abram Demski
Papers from Benja Fallenstein's perspective
Ordered by how strongly the researchers Benja Fallenstein trusts endorse each paper. Same corpus, a different order for every researcher.
- Algorithms for Inverse Reinforcement Learning
- The Basic AI Drives
- The Superintelligent Will: Motivation and Instrumental Rationality in Advanced Artificial Agents
- Superintelligence: Paths, Dangers, Strategies
- Thinking Inside the Box: Controlling and Using an Oracle AI
- Robust Cooperation in the Prisoner's Dilemma: Program Equilibrium via Provability Logic
- A Formal Theory of Inductive Inference. Part II
- Metamagical Themas: Questing for the Essence of Mind and Pattern
- The evolved radio and its implications for modelling the evolution of novel sensors
- Universal Intelligence: A Definition of Machine Intelligence
Their papers
- Robust Cooperation in the Prisoner's Dilemma: Program Equilibrium via Provability Logic (2014) — 30 citations
- Toward Idealized Decision Theory (2015) — 37 citations
- Questions of Reasoning Under Logical Uncertainty (2015)
- Corrigibility (2015) — 177 citations
- Aligning Superintelligence with Human Interests: A Technical Research Agenda (2015)
- Program Equilibrium in the Prisoner ’ s Dilemma via Löb ’ s Theorem (2014)