Niël Conradie

Many recent AI policies have been structured under labels that follow a particular trend: national or international guidelines, policies or regulations, such as the EU’s and USA’s ‘Trustworthy AI’ and China’s and India’s adoption of ‘Responsible AI’, use a label that follows the recipe of [agentially loaded notion + ‘AI’]. A result of this branding, even if implicit, is to encourage the application by laypeople of these agentially loaded notions to the AI technologies themselves. Yet, these notions are appropriate only when applied to agents, which current AI technologies are not; and the concern is that this misapplication creates an incentive to inappropriately attribute trustworthiness or responsibility to AI technologies. We endeavour to show that we have good reason to avoid any general AI policy that uses agentially loaded labelling. We suggest labelling these policies not in terms of some qualification of AI, but rather in terms of our approach to the technology and its wider development and use context – focusing on being trustworthy and responsible about AI, rather than on trustworthy or responsible AI.

Robotic and artificially intelligent (AI) systems are becoming prevalent in our day-to-day lives. As human interaction is increasingly replaced by human–computer and human–robot interaction (HCI and HRI), we occasionally speak and act as though we are blaming or praising various technological devices. While such responses may arise naturally, they are still unusual. Indeed, for some authors, it is the programmers or users—and not the system itself—that we properly hold responsible in these cases. Furthermore, some argue that since directing blame or praise at technology itself is unfitting, designing systems in ways that encourage such practices can only exacerbate the problem. On the other hand, there may be good moral reasons to continue engaging in our natural practices, even in cases involving AI systems or robots. In particular, daily interactions with technology may stand to impact the development of our moral practices in human-to-human interactions. In this paper, we put forward an empirically grounded argument in favor of some technologies being designed for social responsiveness. Although our usual practices will likely undergo adjustments in response to innovative technologies, some systems which we encounter can be designed to accommodate our natural moral responses. In short, fostering HCI and HRI that sustains and promotes our natural moral practices calls for a co-developmental process with some AI and robotic technologies.

The introduction of Autonomous Military Systems (AMS) onto contemporary battlefields raises concerns that they will bring with them the possibility of a techno-responsibility gap, leaving insecurity about how to attribute responsibility in scenarios involving these systems. In this work I approach this problem in the domain of applied ethics with foundational conceptual work on autonomy and responsibility. I argue that concerns over the use of AMS can be assuaged by recognising the richly interrelated context in which these systems will most likely be deployed. This will allow us to move beyond the solely individualist understandings of responsibility at work in most treatments of these cases, toward one that includes collective responsibility. This allows us to attribute collective responsibility to the collectives of which the AMS form a part, and to account for the distribution of burdens that follows from this attribution. I argue that this expansion of our responsibility practices will close at least some otherwise intractable techno-responsibility gaps.

There is a conceptual knot at the intersection of moral responsibility and action theory. This knot can be expressed as the following question: What is the relationship between an agent’s openness to moral responsibility and the intentional status of her behaviour? My answer to this question is developed in three steps. I first develop a control-backed account of intentional agency, one that borrows vital insights from the cognitive sciences – in the form of Dual Process Theory – in understanding the control condition central to the account, and demonstrate that this account fares at least as well as its rivals in the field. Secondly, I investigate the dominant positions in the discussion surrounding the role of control in moral responsibility. After consideration of some shortcomings of these positions – especially the inability to properly account for so-called ambivalence cases – I defend an alternative pluralist account of moral responsibility, in which there are two co-extant variants of such responsibility: attributability and accountability. The latter of these will be shown to have a necessary control condition, also best understood in terms of a requirement for oversight, and in terms of the workings of the dual system mechanism. I then demonstrate how these two accounts are necessarily related through the shared role of this kind of control, leading to my answer to the original question: if an agent is open to moral accountability based on some activity or outcome, this activity or outcome must necessarily have positive intentional status. I then apply this answer in a consideration of certain cases of the use of the Doctrine of Double Effect.