Neil F. Johnson’s research while affiliated with University of Washington and other places

The global chaos caused by the July 19, 2024 technology meltdown highlights the need for a theory of what large-scale cohesive behaviors—dangerous or desirable—could suddenly emerge from future systems of interacting humans, machinery, and software, including artificial intelligence; when they will emerge; and how they will evolve and be controlled. Here, we offer answers by introducing an aggregation model that accounts for the interacting entities’ inter- and intraspecies diversities. It yields a novel multidimensional generalization of existing aggregation physics. We derive exact analytic solutions for the time to cohesion and growth of cohesion for two species, and some generalizations for an arbitrary number of species. These solutions reproduce—and offer a microscopic explanation for—an anomalous nonlinear growth feature observed in various current real-world systems. Our theory suggests good and bad “surprises” will appear sooner and more strongly as humans, machinery, artificial intelligence, and so on interact more, but it also offers a rigorous approach for understanding and controlling this.

Local or national politics can be a catalyst for potentially dangerous hate speech. But with a third of the world’s population eligible to vote in 2024 elections, we need an understanding of how individual-level hate multiplies up to the collective global scale. We show, based on the most recent U.S. presidential election, that offline events are associated with rapid adaptations of the global online hate universe that strengthens both its network-of-networks structure and the types of hate content that it collectively produces. Approximately 50 million accounts in hate communities are drawn closer to each other and to a broad mainstream of billions. The election triggered new hate content at scale around immigration, ethnicity, and antisemitism that aligns with conspiracy theories about Jewish-led replacement. Telegram acts as a key hardening agent; yet, it is overlooked by U.S. Congressional hearings and new E.U. legislation. Because the hate universe has remained robust since 2020, anti-hate messaging surrounding global events (e.g., upcoming elections or the war in Gaza) should pivot to blending multiple hate types while targeting previously untouched social media structures.

Self-assembly is a key process in living systems—from the microscopic biological level (e.g. assembly of proteins into fibrils within biomolecular condensates in a human cell) through to the macroscopic societal level (e.g. assembly of humans into common-interest communities across online social media platforms). The components in such systems (e.g. macromolecules, humans) are highly diverse, and so are the self-assembled structures that they form. However, there is no simple theory of how such structures assemble from a multi-species pool of components. Here we provide a very simple model which trades myriad chemical and human details for a transparent analysis, and yields results in good agreement with recent empirical data. It reveals a new inhibitory role for biomolecular condensates in the formation of dangerous amyloid fibrils, as well as a kinetic explanation of why so many diverse distrust movements are now emerging across social media. The nonlinear dependencies that we uncover suggest new real-world control strategies for such multi-species assembly.

Why humans fight has no easy answer. However, understanding better how humans fight could inform future interventions, hidden shifts and casualty risk. Fusion-fission describes the well-known grouping behavior of fish etc. fighting for survival in the face of strong opponents: they form clusters ('fusion') which provide collective benefits and a cluster scatters when it senses danger ('fission'). Here we show how similar clustering (fusion-fission) of human fighters provides a unified quantitative explanation for complex casualty patterns across decades of Israel-Palestine region violence, as well as the October 7 surprise attack -- and uncovers a hidden post-October 7 shift. State-of-the-art data shows this fighter fusion-fission in action. It also predicts future 'super-shock' attacks that will be more lethal than October 7 and will arrive earlier. It offers a multi-adversary solution. Our results -- which include testable formulae and a plug-and-play simulation -- enable concrete risk assessments of future casualties and policy-making grounded by fighter behavior.

Understanding how harmful content (mis/disinformation, hate, etc.) manages to spread among online communities within and across social media platforms represents an urgent societal challenge. We develop a non-linear dynamical model for such viral spreading, which accounts for the fact that online communities dynamically interconnect across multiple social media platforms. Our mean-field theory (Effective Medium Theory) compares well to detailed numerical simulations and provides a specific analytic condition for the onset of outbreaks (i.e., system-wide spreading). Even if the infection rate is significantly lower than the recovery rate, it predicts system-wide spreading if online communities create links between them at high rates and the loss of such links (e.g., due to moderator pressure) is low. Policymakers should, therefore, account for these multi-community dynamics when shaping policies against system-wide spreading.

Online hate is dynamic, adaptive— and may soon surge with new AI/GPT tools. Establishing how hate operates at scale is key to overcoming it. We provide insights that challenge existing policies. Rather than large social media platforms being the key drivers, waves of adaptive links across smaller platforms connect the hate user base over time, fortifying hate networks, bypassing mitigations, and extending their direct influence into the massive neighboring mainstream. Data indicates that hundreds of thousands of people globally, including children, have been exposed. We present governing equations derived from first principles and a tipping-point condition predicting future surges in content transmission. Using the U.S. Capitol attack and a 2023 mass shooting as case studies, our findings offer actionable insights and quantitative predictions down to the hourly scale. The efficacy of proposed mitigations can now be predicted using these equations.

The highly specialist terms ‘quantum computing’ and ‘quantum information’, together with the broader term ‘quantum technologies’, now appear regularly in the mainstream media. While this is undoubtedly highly exciting for physicists and investors alike, a key question for society concerns such systems’ vulnerabilities – and in particular, their vulnerability to collective manipulation. Here we present and discuss a new form of vulnerability in such systems, that we have identified based on detailed many-body quantum mechanical calculations. The impact of this new vulnerability is that groups of adversaries can maximally disrupt these systems’ global quantum state which will then jeopardize their quantum functionality. It will be almost impossible to detect these attacks since they do not change the Hamiltonian and the purity remains the same; they do not entail any real-time communication between the attackers; and they can last less than a second. We also argue that there can be an implicit amplification of such attacks because of the statistical character of modern non-state actor groups. A countermeasure could be to embed future quantum technologies within redundant classical networks. We purposely structure the discussion in this chapter so that the first sections are self-contained and can be read by non-specialists.

What large-scale cohesive behaviors-desirable or dangerous-can suddenly emerge from systems with interacting humans, machinery and software including AI? When will they emerge? How will they evolve and be controlled? Here we offer some answers to these urgent questions by introducing an aggregation model that accounts for entities' inter-and intra-species diversities. It yields a novel multi-dimensional generalization of existing aggregation physics. We derive exact analytic solutions for the time-to-cohesion and growth-of-cohesion for two species, and some generalizations for an arbitrary number of species. These solutions reproduce-and offer a microscopic explanation for-an anomalous nonlinear growth feature observed in related real-world systems, e.g. Hamas-Hezbollah online support, human-machine team interactions, AI-determined topic coherence. A key takeaway is that good and bad 'surprises' will appear increasingly quickly as humans-machinery-AI etc. mix more-but the theory offers a rigorous approach for understanding and controlling this.

We consider the looming threat of bad actors using artificial intelligence (AI)/Generative Pretrained Transformer to generate harms across social media globally. Guided by our detailed mapping of the online multiplatform battlefield, we offer answers to the key questions of what bad-actor-AI activity will likely dominate, where, when—and what might be done to control it at scale. Applying a dynamical Red Queen analysis from prior studies of cyber and automated algorithm attacks, predicts an escalation to daily bad-actor-AI activity by mid-2024—just ahead of United States and other global elections. We then use an exactly solvable mathematical model of the observed bad-actor community clustering dynamics, to build a Policy Matrix which quantifies the outcomes and trade-offs between two potentially desirable outcomes: containment of future bad-actor-AI activity vs. its complete removal. We also give explicit plug-and-play formulae for associated risk measures.

The prevalence of dangerous misinformation and extreme views online has intensified since the onset of Israel-Hamas war on 7 October 2023. Social media platforms have long grappled with the challenge of providing effective mitigation schemes that can scale to the 5 billion-strong online population. Here, we introduce a novel solution grounded in online network engineering and demonstrate its potential through small pilot studies. We begin by outlining the characteristics of the online social network infrastructure that have rendered previous approaches to mitigating extremes ineffective. We then present our new online engineering scheme and explain how it circumvents these issues. The efficacy of this scheme is demonstrated through a pilot empirical study, which reveals that automatically assembling groups of users online with diverse opinions, guided by a map of the online social media infrastructure, and facilitating their anonymous interactions, can lead to a softening of extreme views. We then employ computer simulations to explore the potential for implementing this scheme online at scale and in an automated manner, without necessitating the contentious removal of specific communities, imposing censorship, relying on preventative messaging, or requiring consensus within the online groups. These pilot studies provide preliminary insights into the effectiveness and feasibility of this approach in online social media settings.