What power-seeking theorems do not show
David Thorstad (Vanderbilt University)
GPI Working Paper No. 27-2024
Recent years have seen increasing concern that artificial intelligence may soon pose an existential risk to humanity. One leading ground for concern is that artificial agents may be power-seeking, aiming to acquire power and in the process disempowering humanity. A range of power-seeking theorems seek to give formal articulation to the idea that artificial agents are likely to be power-seeking. I argue that leading theorems face five challenges, then draw lessons from this result.
Other working papers
Concepts of existential catastrophe – Hilary Greaves (University of Oxford)
The notion of existential catastrophe is increasingly appealed to in discussion of risk management around emerging technologies, but it is not completely clear what this notion amounts to. Here, I provide an opinionated survey of the space of plausibly useful definitions of existential catastrophe. Inter alia, I discuss: whether to define existential catastrophe in ex post or ex ante terms, whether an ex ante definition should be in terms of loss of expected value or loss of potential…
Moral demands and the far future – Andreas Mogensen (Global Priorities Institute, Oxford University)
I argue that moral philosophers have either misunderstood the problem of moral demandingness or at least failed to recognize important dimensions of the problem that undermine many standard assumptions. It has been assumed that utilitarianism concretely directs us to maximize welfare within a generation by transferring resources to people currently living in extreme poverty. In fact, utilitarianism seems to imply that any obligation to help people who are currently badly off is trumped by obligations to undertake actions targeted at improving the value…
Dispelling the Anthropic Shadow – Teruji Thomas (Global Priorities Institute, University of Oxford)
There are some possible events that we could not possibly discover in our past. We could not discover an omnicidal catastrophe, an event so destructive that it permanently wiped out life on Earth. Had such a catastrophe occurred, we wouldn’t be here to find out. This space of unobservable histories has been called the anthropic shadow. Several authors claim that the anthropic shadow leads to an ‘observation selection bias’, analogous to survivorship bias, when we use the historical record to estimate catastrophic risks. …