Learning from Learning Machines: Optimisation, Rules, and Social Norms
This work addresses the problem of achieving moral behavior in AI systems for researchers and policymakers, but it is incremental as it builds on existing analogies without introducing new methods or data.
The paper explores the analogy between machine learning systems and economic entities to understand moral decision-making in AI, suggesting that insights from economics could inform AI safety and vice versa, with deep learning successes indicating implicit specifications may be more effective than explicit ones.
There is an analogy between machine learning systems and economic entities in that they are both adaptive, and their behaviour is specified in a more-or-less explicit way. It appears that the area of AI that is most analogous to the behaviour of economic entities is that of morally good decision-making, but it is an open question as to how precisely moral behaviour can be achieved in an AI system. This paper explores the analogy between these two complex systems, and we suggest that a clearer understanding of this apparent analogy may help us forward in both the socio-economic domain and the AI domain: known results in economics may help inform feasible solutions in AI safety, but also known results in AI may inform economic policy. If this claim is correct, then the recent successes of deep learning for AI suggest that more implicit specifications work better than explicit ones for solving such problems.