Are Robots Sociopaths? A Neuroscientific Approach to the Alignment Problem

Artificial intelligence (AI) is expanding into every niche of human life, organizing our activity, expanding our agency and interacting with us to an exponentially increasing extent. At the same time, AI’s efficiency, complexity and refinement are growing at an accelerating speed. An expanding, ubiquitous intelligence that does not have a means to care about us poses a species-level risk. Justifiably, there is a growing concern with the immediate problem of how to engineer an AI that is aligned with human interests. Computational approaches to the alignment problem currently focus on engineering AI systems to (i) parameterize human values such as harm and flourishing, and (ii) avoid overly drastic solutions, even if these are seemingly optimal. In parallel, ongoing work in applied AI (caregiving, consumer care) is concerned with developing artificial empathy, teaching AI’s to decode human feelings and behavior, and evince appropriate emotional responses.We propose that in the absence of affective empathy (which allows us to share in the states of others), existing approaches to artificial empathy may fail to reliably produce the pro-social, caring component of empathy, potentially resulting in increasingly cognitively complex sociopaths. We adopt the colloquial usage of the term “sociopath” to signify an intelligence possessing cognitive empathy (i.e., the ability to decode, infer, and model the mental and affective states of others), but crucially lacking pro-social, empathic concern arising from shared affect and embodiment. It is widely acknowledged that aversion to causing harm is foundational to the formation of empathy and moral behavior. However, harm aversion is itself predicated on the experience of harm, within the context of the preservation of physical integrity. Following from this, we argue that a “top-down” rule-based approach to achieving caring AI may be inherently unable to anticipate and adapt to the inevitable novel moral/logistical dilemmas faced by an expanding AI. Crucially, it may be more effective to coax caring to emerge from the bottom up, baked into an embodied, vulnerable artificial intelligence with an incentive to preserve its physical integrity. This may be achieved via iterative optimization within a series of tailored environments with incentives and contingencies inspired by the development of empathic concern in humans. Here we attempt an outline of what these training steps might look like. We speculate that work of this kind may allow for AI that surpasses empathic fatigue and the idiosyncrasies, biases, and computational limits that restrict human empathy. While for us, “a single death is a tragedy, a million deaths are a statistic”, the scaleable complexity of AI may allow it to deal proportionately with complex, large-scale ethical dilemmas. Hopefully, by addressing this problem seriously in the early stages of AI’s integration with society, we may one day be accompanied by AI that plans and behaves with a deeply ingrained weight placed on the welfare of others, coupled with the cognitive complexity necessary to understand and solve extraordinary problems.

Beliefs in Misinformation and Conspiracy Theories About COVID- 19: a Triangular Relationship Between Analytic Thinking, Depressive States, and Misperception

Beliefs about misinformation and conspiracy theories are often associated with a state of mind. With the spread of the pandemic there has been an outbreak of depression cases among the population. In this paper, we attempt to test the relationship between affective states and beliefs in misinformation about COVID-19 during the early phase of the pandemic. We do this through a survey carried out on a random and representative sample of the Italian population that allows us to go and verify the co-evolution of many factors: i.e., beliefs in misinformation, symptoms of depression, perceptions and misperceptions about COVID-19, ways in which citizens got informed about the pandemic, and sociodemographic characteristics (e.g., age, gender, education). The results show that the relationship between affective state and beliefs in misinformation exists but is more complex than hypothesized.

The Predictive Dynamics of Happiness and Well-Being

We offer an account of mental health and well-being using the predictive processing framework (PPF). According to this framework, the difference between mental health and psychopathology can be located in the goodness of the predictive model as a regulator of action. What is crucial for avoiding the rigid patterns of thinking, feeling and acting associated with psychopathology is the regulation of action based on the valence of affective states. In PPF, valence is modelled as error dynamics—the change in prediction errors over time . Our aim in this paper is to show how error dynamics can account for both momentary happiness and longer term well-being. What will emerge is a new neurocomputational framework for making sense of human flourishing.

Daily Reports of Aggressive Behaviors in Interpersonal Conflicts

Interpersonal conflicts are inevitable, but the probability that conflicts involve aggressive behavior varies. Prior research that has tended to focus on victimization in intimate partnerships reported through retrospective designs. Addressing these limitations, the current study examines daily reports of behaving aggressively in any conflict across relationships in a sample of 512 young adults drawn from the nationally representative iCOR cohort. Respondent attitudes and affective measures were collected at the end of the daily data collection period. Regression methods were applied to examine the probability and frequency of aggression, investigating early and recent exposure to adversities, attitudes, self-control, affect and emotional states, and alcohol use behavior. Recent adversities and the propensity to endorse a defensive honor code attitude, consistent with theory and retrospective studies of aggression, predicted both prevalence and frequency of aggressive behavior. The associations of childhood maltreatment and self-control with the prevalence of behaving aggressively were as expected, but these constructs were significantly associated with the frequency of aggression with unexpected, inverse directionality. Moreover, respondents’ affect and other emotional states were only associated with the frequency, not the prevalence, of aggressive behavior. Overall, this daily data collection constructively distinguished risk and protective factors for behaving aggressively more often. Further research is needed to disentangle the extent to which affective states drive or is a consequence of frequent aggressive behavior.

The Rhetoric of Hobbes's Translation of Thucydides

In several key passages in Thomas Hobbes's understudied translation of Thucydides's History of the Peloponnesian War, Hobbes's Pericles directs audiences to distrust rhetoric in favor of calculative self-interest, inward-focused affective states, and an epistemic reliance on sovereignty. Hobbes's own intervention via his translation of Thucydides involves similar rhetorical moves. By directing readers to learn from Thucydides, Hobbes conceals his own rhetorical appeals in favor of sovereignty while portraying rhetoric undermining sovereignty as manipulative, self-serving, and representative of the entire category of “rhetoric.” Hobbes's double redescription of rhetoric is an important starting point for an early modern project: appeals that justify a desired political order are characterized as “right reason,” “the law of nature,” or “enlightenment,” while rhetoric constituting solidarities or publics outside the desired order is condemned. Hobbes's contribution to this project theorizes rhetoric as a barrier to individual calculations of interest, placing a novel constraint on political life.

When self comes to a wandering mind: Brain representations and dynamics of self-generated concepts in spontaneous thought

Self-relevant concepts are major building blocks of spontaneous thought, and their dynamics in a natural stream of thought are likely to reveal one's internal states important for mental health. Here we conducted an fMRI experiment (n = 62) to examine brain representations and dynamics of self-generated concepts in the context of spontaneous thought using a newly developed free association-based thought sampling task. The dynamics of conceptual associations were predictive of individual differences in general negative affectivity, replicating across multiple datasets (n = 196). Reflecting on self-generated concepts strongly engaged brain regions linked to autobiographical memory, conceptual processes, emotion, and autonomic regulation, including the medial prefrontal and medial temporal subcortical structures. Multivariate pattern-based predictive modeling revealed that the neural representations of valence became more person-specific as the level of perceived self-relevance increased. Overall, this study provides a hint of how self-generated concepts in spontaneous thought construct inner affective states and idiosyncrasies.

Happiness as a Measure of Mental Health – Validation of the Portuguese Version of the Oxford Happiness Questionnaire

Background: Happiness is a complex concept that has been associated with mental health. Measures of happiness incorporate affective states predisposition and personality traits. Following the link established between subjective wellbeing and positive emotions and mental health, the Oxford Happiness Questionnaire (OHQ) may be considered a broad measure of personal happiness. We aimed to validate OHQ in the Portuguese speaking population. METHODS: A sample of 421 young adults fulfilled the 29 and 8-item items of OHQ Portuguese version. Participants also completed the Perceived Stress Scale, Subjective Happiness Scale and the Hospital Anxiety and Depression Scale. A principal component analysis with Varimax rotation, Kaiser rule, complemented by a scree plot graphical representation, was performed. RESULTS: Seven components of the OHQ explained 58.22% of the total variance, and a correlation of 0.90 between the long 29 items version and the 8 items short version. Both versions related inversely with negative feelings (depression, anxiety, and stress), and directly with subjective happiness. CONCLUSION: The OHQ performs as a happiness assessment tool suitable for patients and healthy populations. The application of this questionnaire may furthermore contribute to clarify the concept of happiness and test the real usefulness of these tools in the clinical setting.

Toward a Theory of Emotions in Competitive Sports

In this article, we introduce a theory on the dynamic development of affective processes, affect regulation, and the relationship between emotions and sport performance. The theory focusses on how affective processes emerge and develop during competitive sport involvement. Based on Scherer’s component process model, we postulate six components of emotion that interact with each other in a circular fashion: (I) triggering processes, (II) physiological reactions, (III) action tendencies, (IV) expressive behaviors, (V) subjective experience, and (VI) higher cognitive processes. The theory stresses the dynamics of affective processes and describes the consequences for performance in competitive sports. It assumes that the peculiarities of different sports must be taken into account in order to understand the affective processes, and offers starting points on which strategies can be used to effectively regulate affective states. Consequences for research and practice are derived and discussed. To study the development of affective processes, future research should test the assumptions in ecologically valid contexts, such as real competitions or competition-like situations, using multi-component measures of emotions.