Evolutionary debunking and value alignment
Michael T. Dale (Hampden-Sydney College) and Bradford Saad (Global Priorities Institute, University of Oxford)
GPI Working Paper No. 11-2024
This paper examines the bearing of evolutionary debunking arguments—which use the evolutionary origins of values to challenge their epistemic credentials—on the alignment problem, i.e. the problem of ensuring that highly capable AI systems are properly aligned with values. Since evolutionary debunking arguments are among the best empirically-motivated arguments that recommend changes in values, it is unsurprising that they are relevant to the alignment problem. However, how evolutionary debunking arguments bear on alignment is a neglected issue. This paper sheds light on that issue by showing how evolutionary debunking arguments: (1) raise foundational challenges to posing the alignment problem, (2) yield normative constraints on solving it, and (3) generate stumbling blocks for implementing solutions. After mapping some general features of this philosophical terrain, we illustrate how evolutionary debunking arguments interact with some of the main technical approaches to alignment. To conclude, we motivate a parliamentary approach to alignment and suggest some ways of developing and testing it.
Other working papers
How effective is (more) money? Randomizing unconditional cash transfer amounts in the US – Ania Jaroszewicz (University of California San Diego), Oliver P. Hauser (University of Exeter), Jon M. Jachimowicz (Harvard Business School) and Julian Jamison (University of Oxford and University of Exeter)
We randomized 5,243 Americans in poverty to receive a one-time unconditional cash transfer (UCT) of $2,000 (two months’ worth of total household income for the median participant), $500 (half a month’s income), or nothing. We measured the effects of the UCTs on participants’ financial well-being, psychological well-being, cognitive capacity, and physical health through surveys administered one week, six weeks, and 15 weeks later. While bank data show that both UCTs increased expenditures, we find no evidence that…
Will AI Avoid Exploitation? – Adam Bales (Global Priorities Institute, University of Oxford)
A simple argument suggests that we can fruitfully model advanced AI systems using expected utility theory. According to this argument, an agent will need to act as if maximising expected utility if they’re to avoid exploitation. Insofar as we should expect advanced AI to avoid exploitation, it follows that we should expected advanced AI to act as if maximising expected utility. I spell out this argument more carefully and demonstrate that it fails, but show that the manner of its failure is instructive…
The scope of longtermism – David Thorstad (Global Priorities Institute, University of Oxford)
Longtermism holds roughly that in many decision situations, the best thing we can do is what is best for the long-term future. The scope question for longtermism asks: how large is the class of decision situations for which longtermism holds? Although longtermism was initially developed to describe the situation of…