3 citations · 3 across the 4 of their papers we have counts for
4 papers
Against Proxy Optimization
Sven Neth
I discuss conditions under which maximizing a proxy utility function is harmful and suggest this poses problems for applying decision theory.
Off-Switching Not Guaranteed
Sven Neth
Hadfield-Menell et al. (2017) propose the Off-Switch Game, a model of Human-AI cooperation in which AI agents always defer to humans because they are uncertain about our preference…
Better Foundations for Subjective Probability
Sven Neth
How do we ascribe subjective probability? In decision theory, this question is often addressed by representation theorems, going back to Ramsey (1926), which tell us how to define…
Rational Aversion to Information
Sven Neth
Is more information always better? Or are there some situations in which more information can make us worse off? Good (1967) argues that expected utility maximizers should always a…