Whether it would take one decade or several centuries, many agree that it is possible to create a *superintelligence*---an artificial intelligence with a godlike ability to achieve its goals. And many who have reflected carefully on this fact agree that our best hope for a "friendly" superintelligence is to design it to *learn* values like ours, since our values are too complex to program or hardwire explicitly. But the value learning approach to AI safety faces three particularly philosophical puzzles: first, (...) it is unclear how any intelligent system could learn its final values, since to judge one supposedly "final" value against another seems to require a further background standard for judging. Second, it is unclear how to determine the content of a system's values based on its physical or computational structure. Finally, there is the distinctly ethical question of which values we should best aim for the system to learn. I outline a potential answer to these interrelated puzzles, centering on a "miktotelic" proposal for blending a complex, learnable final value out of many simpler ones. (shrink)

This manuscript examines two accounts that discuss rights disputes. On the one hand, Russ Shafer-Landau argues for specificationism (or what is referred to here as SA), which deems rights as having innate limitations. One the other, Judith Jarvis Thomson defends infringement theory (or what is referred to here as IVA), which views rights to be competing factors. Shafer-Landau in “Specifying Absolute Rights” endeavored to discredit Thomson’s IVA and promote his favored theory. This material responds to and criticizes the claims (...) Shafer-Landau pressed in his article. First part of the thesis addresses his concerns and finds them unconvincing. Using tools of logic, it is demonstrated that Shafer-Landau’s demands on compensation are without warrant. More than this, his demands on the tripartite are misguided. Second part tackles some shortcomings of SA. One of which is the finding that two of the three arguments Shafer-Landau posited for SA’s superiority run counter to each other. Should Shafer-Landau save one, it would remain untenable for the foundations therein rest on a mistake. Finally, his position of SA being sufficiently explanatory is in itself wanting. Though this material does not go as far as proving which theory is practically better, the project is not bereft of purpose. By the end, IVA would already have been relieved of the criticisms whereas SA would be confronted with multiple challenges. (shrink)