Olle Häggström’s research while affiliated with Chalmers University of Technology and other places

It has sometimes been suggested that lack of common sense in present-day AI systems demonstrates that there is no need to be concerned about future scenarios where a powerful unaligned AI seizes control of the world from us humans. This argument is criticized, and the confusion is shown to stem partly from an overly one-sided focus on artificial general intelligence (AGI), along with the implicit and unwarranted assumption that AGI must be attained before any such drastic scenarios can be realized.

This book gathers contributions from the fourth edition of the Conference on "Philosophy and Theory of Artificial Intelligence" (PT-AI), held on 27-28th of September 2021 at Chalmers University of Technology, in Gothenburg, Sweden. It covers topics at the interface between philosophy, cognitive science, ethics and computing. It discusses advanced theories fostering the understanding of human cognition, human autonomy, dignity and morality, and the development of corresponding artificial cognitive structures, analyzing important aspects of the relationship between humans and AI systems, including the ethics of AI. This book offers a thought-provoking snapshot of what is currently going on, and what are the main challenges, in the multidisciplinary field of the philosophy of artificial intelligence.

The by now standard argument put forth by Yudkowsky, Bostrom and others for why the possibility of a carelessly handled AI breakthrough poses an existential threat to humanity is shown through careful conceptual analysis to be very much alive and kicking, despite the suggestion in a recent paper by M\"uller and Cannon that the argument contains a flaw.

Mind uploading is the hypothetical future technology of transferring human minds to computer hardware using whole-brain emulation. After a brief review of the technological prospects for mind uploading, a range of philosophical and ethical aspects of the technology are reviewed. These include questions about whether uploads will have consciousness and whether uploading will preserve personal identity, as well as what impact on society a working uploading technology is likely to have and whether these impacts are desirable. The issue of whether we ought to move forward towards uploading technology remains as unclear as ever.

An artificial general intelligence (AGI) might have an instrumental drive to modify its utility function to improve its ability to cooperate, bargain, promise, threaten, and resist and engage in blackmail. Such an AGI would necessarily have a utility function that was at least partially observable and that was influenced by how other agents chose to interact with it. This instrumental drive would conflict with the strong orthogonality thesis since the modifications would be influenced by the AGI’s intelligence. AGIs in highly competitive environments might converge to having nearly the same utility function, one optimized to favorably influencing other agents through game theory. Nothing in our analysis weakens arguments concerning the risks of AGI.

An artificial general intelligence (AGI) might have an instrumental drive to modify its utility function to improve its ability to cooperate, bargain, promise, threaten, and resist and engage in blackmail. Such an AGI would necessarily have a utility function that was at least partially observable and that was influenced by how other agents chose to interact with it. This instrumental drive would conflict with the orthogonality thesis since the modifications would be influenced by the AGI's intelligence. AGIs in highly competitive environments might converge to having nearly the same utility function, one optimized to favorably influencing other agents through game theory.

Purpose This paper aims to formalize long-term trajectories of human civilization as a scientific and ethical field of study. The long-term trajectory of human civilization can be defined as the path that human civilization takes during the entire future time period in which human civilization could continue to exist. Design/methodology/approach This paper focuses on four types of trajectories: status quo trajectories, in which human civilization persists in a state broadly similar to its current state into the distant future; catastrophe trajectories, in which one or more events cause significant harm to human civilization; technological transformation trajectories, in which radical technological breakthroughs put human civilization on a fundamentally different course; and astronomical trajectories, in which human civilization expands beyond its home planet and into the accessible portions of the cosmos. Findings Status quo trajectories appear unlikely to persist into the distant future, especially in light of long-term astronomical processes. Several catastrophe, technological transformation and astronomical trajectories appear possible. Originality/value Some current actions may be able to affect the long-term trajectory. Whether these actions should be pursued depends on a mix of empirical and ethical factors. For some ethical frameworks, these actions may be especially important to pursue.

Purpose This paper aims to contribute to the futurology of a possible artificial intelligence (AI) breakthrough, by reexamining the Omohundro–Bostrom theory for instrumental vs final AI goals. Does that theory, along with its predictions for what a superintelligent AI would be motivated to do, hold water? Design/methodology/approach The standard tools of systematic reasoning and analytic philosophy are used to probe possible weaknesses of Omohundro–Bostrom theory from four different directions: self-referential contradictions, Tegmark’s physics challenge, moral realism and the messy case of human motivations. Findings The two cornerstones of Omohundro–Bostrom theory – the orthogonality thesis and the instrumental convergence thesis – are both open to various criticisms that question their validity and scope. These criticisms are however far from conclusive: while they do suggest that a reasonable amount of caution and epistemic humility is attached to predictions derived from the theory, further work will be needed to clarify its scope and to put it on more rigorous foundations. Originality/value The practical value of being able to predict AI goals and motivations under various circumstances cannot be overstated: the future of humanity may depend on it. Currently, the only framework available for making such predictions is Omohundro–Bostrom theory, and the value of the present paper is to demonstrate its tentative nature and the need for further scrutiny.