Cheating Death in Damascus

Levinstein, Benjamin A.; Soares, Nate

doi:10.5840/jphil2020117516

Cited by 12 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In light of the issues discussed so far, one may question whether traditional approaches to decision and game theory are an ideal fit for the problem of designing artificially intelligent agents. One concrete new form of decision theory that has been proposed in this context is that of functional decision theory (FDT) (Levinstein and Soares 2017). This is in contrast to the more standard decision theory that dominates economic theory, known in the philosophy literature as causal decision theory (CDT), but also in contrast to evidential decision theory (EDT), another theory that has been thoroughly studied in the philosophy literature.…”

Section: Beyond Causal Decision Theorymentioning

confidence: 99%

Designing Preferences, Beliefs, and Identities for Artificial Intelligence

Conitzer

2019

AAAI

View full text Add to dashboard Cite

Research in artificial intelligence, as well as in economics and other related fields, generally proceeds from the premise that each agent has a well-defined identity, well-defined preferences over outcomes, and well-defined beliefs about the world. However, as we design AI systems, we in fact need to specify where the boundaries between one agent and another in the system lie, what objective functions these agents aim to maximize, and to some extent even what belief formation processes they use. The premise of this paper is that as AI is being broadly deployed in the world, we need well-founded theories of, and methodologies and algorithms for, how to design preferences, identities, and beliefs. This paper lays out an approach to address these problems from a rigorous foundation in decision theory, game theory, social choice theory, and the algorithmic and computational aspects of these fields.

show abstract

Section: Beyond Causal Decision Theorymentioning

confidence: 99%

Designing Preferences, Beliefs, and Identities for Artificial Intelligence

Conitzer

2019

AAAI

View full text Add to dashboard Cite

show abstract

“…1717For recent philosophically accessible formulations of fdt , see Levinstein and Soares (2020) and Soares and Yudkowsky (2018). …”

mentioning

confidence: 99%

“…This is seen clearly in prediction cases like Newcomb's problem, where fdt views changes to the output of one's decision algorithm as sometimes necessitating changes to what has been predicted (where such an effect is due to the decision algorithm the agent “accepts” and not the act the agent performs). (See Soares and Yudkowsky (2018) and Levinstein and Soares (2020) for more on this aspect of fdt .) Nevertheless, as we have emphasized in the text, gac also differs significantly from acceptance‐based rule consequentialism.…”

mentioning

confidence: 99%

Act Consequentialism without Free Rides

Greene¹,

Levinstein

2020

Philosophical Perspectives

Self Cite

View full text Add to dashboard Cite

Consequentialist theories determine rightness solely based on real or expected consequences. Although such theories are popular, they often have difficulty with generalizing intuitions, which demand concern for questions like “What if everybody did that?” Rule consequentialism attempts to incorporate these intuitions by shifting the locus of evaluation from the consequences of acts to those of rules. However, detailed rule‐consequentialist theories seem ad hoc or arbitrary compared to act consequentialist ones. We claim that generalizing can be better incorporated into consequentialism by keeping the locus of evaluation on acts but adjusting the decision theory behind act selection. Specifically, we should adjust which types of dependencies the theory takes to be decision‐relevant. Using this strategy, we formulate a new theory, generalized act consequentialism, which we argue is more compelling than rule consequentialism both in modeling the actual reasoning of generalizers and in delivering correct verdicts.

show abstract

The consequentialist problem with prepunishment

Greene

2021

Thought: A Journal of Philosophy

View full text Add to dashboard Cite

This paper targets a nearly universal assumption in the philosophical literature: that prepunishment is unproblematic for consequentialists. Prepunishment threats do not deter, as deterrence is traditionally conceived. In fact, a pure prepunishment legal system would tend to increase the criminal disposition of the grudgingly compliant. This is a serious problem since, from many perspectives, but especially from a consequentialist one, a primary purpose of punishment is deterrence. I analyze the decision theory behind preand postpunishments, which helps clarify both what deterrence is and how it operates in consequentialist justifications of punishment. I end by sketching a road map for the future of prepunishment as artificial intelligence and other technological advances generate increasing possibilities for its use.

show abstract

Cheating Death in Damascus

Cited by 12 publications

References 14 publications

Designing Preferences, Beliefs, and Identities for Artificial Intelligence

Designing Preferences, Beliefs, and Identities for Artificial Intelligence

Act Consequentialism without Free Rides

The consequentialist problem with prepunishment

Contact Info

Product

Resources

About