Catastrophic risk raises questions that are not only of practical importance, but also of great philosophical interest, such as how to define catastrophe and what distinguishes catastrophic outcomes from non-catastrophic ones. Catastrophic risk also raises questions about how to rationally respond to such risks. How to rationally respond arguably partly depends on the severity of the uncertainty, for instance, whether quantitative probabilistic information is available, or whether only comparative likelihood information is available, or neither (...) type of information. Finally, catastrophic risk raises important ethical questions about what to do when catastrophe avoidance conflicts with equity promotion. (shrink)

A classification of the global catastrophic risks of AI is presented, along with a comprehensive list of previously identified risks. This classification allows the identification of several new risks. We show that at each level of AI’s intelligence power, separate types of possible catastrophes dominate. Our classification demonstrates that the field of AI risks is diverse, and includes many scenarios beyond the commonly discussed cases of a paperclip maximizer or robot-caused unemployment. Global catastrophic failure could happen at various (...) levels of AI development, namely, before it starts self-improvement, during its takeoff, when it uses various instruments to escape its initial confinement, or after it successfully takes over the world and starts to implement its goal system, which could be plainly unaligned, or feature-flawed friendliness. AI could also halt at later stages of its development either due to technical glitches or ontological problems. Overall, we identified around several dozen scenarios of AI-driven global catastrophe. The extent of this list illustrates that there is no one simple solution to the problem of AI safety, and that AI safety theory is complex and must be customized for each AI development level. (shrink)

Recent progress in artificial intelligence (AI) has drawn attention to the technology’s transformative potential, including what some see as its prospects for causing large-scale harm. We review two influential arguments purporting to show how AI could pose catastrophic risks. The first argument — the Problem of Power-Seeking — claims that, under certain assumptions, advanced AI systems are likely to engage in dangerous power-seeking behavior in pursuit of their goals. We review reasons for thinking that AI systems might seek power, (...) that they might obtain it, that this could lead to catastrophe, and that we might build and deploy such systems anyway. The second argument claims that the development of human-level AI will unlock rapid further progress, culminating in AI systems far more capable than any human — this is the Singularity Hypothesis. Power-seeking behavior on the part of such systems might be particularly dangerous. We discuss a variety of objections to both arguments and conclude by assessing the state of the debate. (shrink)

Abstract: Global chemical contamination is an underexplored source of global catastrophic risks that is estimated to have low a priori probability. However, events such as pollinating insects’ population decline and lowering of the human male sperm count hint at some toxic exposure accumulation and thus could be a global catastrophic risk event if not prevented by future medical advances. We identified several potentially dangerous sources of the global chemical contamination, which may happen now or could happen in (...) the future: autocatalytic reactions, exposure to multiple subthreshold sources, and long-term unintended consequences, arising from both natural and bioengineered sources. We list several especially dangerous chemicals—dioxin, organiс compounds, and toxic heavy metals. We also discuss the features of such dangerous chemicals—molecules that can stay in the biosphere for a long time and affect it over time. We explore several social processes and scenarios where global chemical contamination becomes possible: large natural catastrophe like meteorite impact, supervolcano eruption, new ways of predicting properties of the chemicals via machine learning and their manufacturing via synthetic biology, uncontrolled “capitalistic” economic development with a corresponding large waste production, quick adoption of many chemicals with unknown long-term properties and unintended side-effects. These are all low probability, so work on other global catastrophic risks should be prioritized, but chemical risks could exacerbate other types of catastrophe contributing to social collapse. (shrink)

In this article, a classification of the global catastrophic risks connected with the possible existence (or non-existence) of extraterrestrial intelligence is presented. If there are no extra-terrestrial intelligences (ETIs) in our light cone, it either means that the Great Filter is behind us, and thus some kind of periodic sterilizing natural catastrophe, like a gamma-ray burst, should be given a higher probability estimate, or that the Great Filter is ahead of us, and thus a future global catastrophe is high (...) probability. If ETIs exist in our light cone, it is most likely they exist in the form of ET artificial general intelligence (ETAI). ETAI may be traveling at near-light speed as an explosive wave of intelligence in the form of some nano-mechanisms which could reach us at any moment; may send us potentially dangerous messages with AI-virus payloads; or be near or on Earth in some dormant form. This dormant form could be nanobots, which could act as berserkers, and be triggered when humans unwittingly cross some threshold. If ETIs are nearby and less advanced, they could find our messaging extra-terrestrial intelligence (METI) messages and send their “fleet” to or direct weapons toward Earth. Even extinct ETIs could have left dangerous remnants in the form of AI systems that our civilization may encounter. If our existence is a simulation, this could be run by ETIs. Even a false belief in the existence of ETIs could potentially fuel millennial sects. If humanity is the first intelligence to emerge, it may kill or prevent the existence of all future potential ETI, a different type of catastrophe. Several options to prevent catastrophic risks are connected with ETI: sending requests for help, using random strategies to escape the Fermi paradox, Great Filter prediction, or the hope that ETIs will find the remains of our extinct civilization and resurrect it. (shrink)

Abstract: After 2017 NY Times publication, the stigma of the scientific discussion of the problem of so-called UAP (Unidentified Aerial Phenomena) was lifted. Now the question arises: how UAP will affect the future of humanity, and especially, the probability of the global catastrophic risks? To answer this question, we assume that the Nimitz case in 2004 was real and we will suggest a classification of the possible explanations of the phenomena. The first level consists of mundane explanations: hardware glitches, (...) malfunction, hoaxes and lies. The second level involves explanations which are not changing completely our model of the world, but only updating it: new military tech, large psyop operation or new physical effect like ball lightning. The third level of explanations requires a complete overhaul of our world model and includes a large set of fantastic hypothesis: alien starships, interdimensional beings, glitches in the matrix, projections from the collective unconsciousness, Boltzmann brain’s experiences etc. The higher is the level of the hypothesis, the less probable it is, but the bigger is its consequences for possible global catastrophic risks. Thus, “integrating” over the field of all possible explanations, we find that UAP increases catastrophic risks. Technological progress increases our chances of direct confrontation with the phenomena. If the phenomenon has intelligence, the change of its behavior could be unexpected after we pass some unknown threshold. But we could lower the risks if we assume some reasonable policy of escaping confrontations. (shrink)

Advocates of longtermism point out that interventions which focus on improving the prospects of people in the very far future will, in expectation, bring about a significant amount of good. Indeed, in expectation, such long-term interventions bring about far more good than their short-term counterparts. As such, longtermists claim we have compelling moral reason to prefer long-term interventions. In this paper, I show that longtermism is in conflict with plausible deontic scepticism about aggregation. I do so by demonstrating that, from (...) both an ex-ante and ex-post perspective, longtermist interventions – and, in particular, those which aim to mitigate catastrophic risk – typically generate extremely weak claims of assistance from future people. (shrink)

Suppose that a decision-maker's aim, under certainty, is to maximise some continuous value, such as lifetime income or continuous social welfare. Can such a decision-maker rationally satisfy what has been called "continuity for easy cases" while at the same time satisfying what seems to be a widespread intuition against the full-blown continuity axiom of expected utility theory? In this note I argue that the answer is "no": given transitivity and a weak trade-off principle, continuity for easy cases violates the anti-continuity (...) intuition. I end the note by exploring an even weaker continuity condition that is consistent with the aforementioned intuition. (shrink)

Abstract: This article examines risks associated with the program of passive search for alien signals (Search for Extraterrestrial Intelligence, or SETI) connected with the possibility of finding of alien transmission which includes description of AI system aimed on self-replication (SETI-attack). A scenario of potential vulnerability is proposed as well as the reasons why the proportion of dangerous to harmless signals may be high. The article identifies necessary conditions for the feasibility and effectiveness of the SETI-attack: ETI existence, possibility of AI, (...) small size of the Seed AI, small speed of physical interstellar travel and large distance between civilizations. Needed additions to the SETI protocol are considered: keep the signal existence, its content and source location in secret, don’t run alien programs, jam dangerous signals, wait until creation of humanity’s own AI. In addition, scenarios in which it may be reasonable to start an alien AI (if it has been downloaded) are explored. (shrink)

Recently criticisms against autonomous weapons were presented in a video in which an AI-powered drone kills a person. However, some said that this video is a distraction from the real risk of AI—the risk of unlimitedly self-improving AI systems. In this article, we analyze arguments from both sides and turn them into conditions. The following conditions are identified as leading to autonomous weapons becoming a global catastrophic risk: 1) Artificial General Intelligence (AGI) development is delayed relative (...) to progress in narrow AI and manufacturing. 2) The potential for very cheap manufacture of drones, with prices below 1 USD each. 3) Anti-drone defense capabilities lagging offensive development. 4) Special global military posture encouraging development of drone swarms as a strategic offensive weapon, able to kill civilians. We conclude that while it is unlikely that drone swarms alone will become existential risk, lethal autonomous weapons could contribute to civilizational collapse in case of new world war. (shrink)

Many global catastrophic and existential risks (X-risks) threaten the existence of humankind. There are also many ideas for their prevention, but the meta-problem is that these ideas are not structured. This lack of structure means it is not easy to choose the right plan(s) or to implement them in the correct order. I suggest using a “Plan A, Plan B” model, which has shown its effectiveness in planning actions in unpredictable environments. In this approach, Plan B is a backup (...) option, implemented if Plan A fails. In the case of global risks, Plan A is intended to prevent a catastrophe and Plan B to survive it, if it is not avoided. Each plan has similar stages: analysis, planning, funding, low-level realization and high-level realization. Two variables—plans and stages—provide an effective basis for classification of all possible X-risks prevention methods in the form of a two-dimensional map, allowing the choice of optimal paths for human survival. I have created a framework for estimating the utility of various prevention methods based on their probability of success, the chances that they will be realized in time, their opportunity cost, and their risk. I also distinguish between top-down and bottom-up approaches. (shrink)

Existential risks threaten the future of humanity, but they are difficult to measure. However, to communicate, prioritize and mitigate such risks it is important to estimate their relative significance. Risk probabilities are typically used, but for existential risks they are problematic due to ambiguity, and because quantitative probabilities do not represent some aspects of these risks. Thus, a standardized and easily comprehensible instrument is called for, to communicate dangers from various global catastrophic and existential risks. In this article, (...) inspired by the Torino scale of asteroid danger, we suggest a color coded scale to communicate the magnitude of global catastrophic and existential risks. The scale is based on the probability intervals of risks in the next century if they are available. The risks’ estimations could be adjusted based on their severities and other factors. The scale covers not only existential risks, but smaller size global catastrophic risks. It consists of six color levels, which correspond to previously suggested levels of prevention activity. We estimate artificial intelligence risks as “red”, while “orange” risks include nanotechnology, synthetic biology, full scale nuclear war and a large global agricultural shortfall (caused by regional nuclear war, coincident extreme weather, etc.) The risks of natural pandemic, supervolcanic eruption and global warming are marked as “yellow” and the danger from asteroids is “green”. -/- Keywords: global catastrophic risks; existential risks; Torino scale; policy; risk probability . (shrink)

Pandemics have been suggested as global risks many times, but it has been shown that the probability of human extinction due to one pandemic is small, as it will not be able to affect and kill all people, but likely only half, even in the worst cases. Assuming that the probability of the worst pandemic to kill a person is 0.5, and assuming linear interaction between different pandemics, 30 strong pandemics running simultaneously will kill everyone. Such situations cannot happen naturally, (...) but because biotechnology is developing analogously to Moore’s law, it may become possible in the near future (10-50 years from now), because of biohackers, CRISPR, bioprinters, AI-assisted DNA-programing, and weapons of “knowledge-enabled mass destruction” published on the Internet. It could also happened in case of large-scale biological war, or if a rogue country released its entire biological arsenal simultaneously. We also will address other scenarios and risk increasing factors as well as mitigation and adaptation strategies. (shrink)

Recent advances in natural language processing have given rise to a new kind of AI architecture: the language agent. By repeatedly calling an LLM to perform a variety of cognitive tasks, language agents are able to function autonomously to pursue goals specified in natural language and stored in a human-readable format. Because of their architecture, language agents exhibit behavior that is predictable according to the laws of folk psychology: they function as though they have desires and beliefs, and then make (...) and update plans to pursue their desires given their beliefs. We argue that the rise of language agents significantly reduces the probability of an existential catastrophe due to loss of control over an AGI. This is because the probability of such an existential catastrophe is proportional to the difficulty of aligning AGI systems, and language agents significantly reduce that difficulty. In particular, language agents help to resolve three important issues related to aligning AIs: reward misspecification, goal misgeneralization, and uninterpretability. (shrink)

Many researchers have argued that humanity will create artificial general intelligence (AGI) within the next twenty to one hundred years. It has been suggested that AGI may inflict serious damage to human well-being on a global scale ('catastrophic risk'). After summarizing the arguments for why AGI may pose such a risk, we review the fieldʼs proposed responses to AGI risk. We consider societal proposals, proposals for external constraints on AGI behaviors and proposals for creating AGIs that (...) are safe due to their internal design. (shrink)

This paper discusses ethical issues surrounding Integrated Assessment Models (IAMs) of the economic effects of climate change, and how climate economists acting as policy advisors ought to represent the uncertain possibility of catastrophe. Some climate economists, especially Martin Weitzman, have argued for a precautionary approach where avoiding catastrophe should structure climate economists’ welfare analysis. This paper details ethical arguments that justify this approach, showing how Weitzman’s “fat tail” probabilities of climate catastrophe pose ethical problems for widely used IAMs. The main (...) claim is that economists who ignore or downplay catastrophic risks in their representations of uncertainty likely fall afoul of ethical constraints on scientists acting as policy advisors. Such scientists have duties to honestly articulate uncertainties and manage (some) inductive risks, or the risks of being wrong in different ways. (shrink)

Longtermists have argued that humanity should significantly increase its efforts to prevent catastrophes like nuclear wars, pandemics, and AI disasters. But one prominent longtermist argument overshoots this conclusion: the argument also implies that humanity should reduce the risk of existential catastrophe even at extreme cost to the present generation. This overshoot means that democratic governments cannot use the longtermist argument to guide their catastrophe policy. In this paper, we show that the case for preventing catastrophe does not depend on (...) longtermism. Standard cost-benefit analysis implies that governments should spend much more on reducing catastrophic risk. We argue that a government catastrophe policy guided by cost-benefit analysis should be the goal of longtermists in the political sphere. This policy would be democratically acceptable, and it would reduce existential risk by almost as much as a strong longtermist policy. (shrink)

Recently many methods for reducing the risk of human extinction have been suggested, including building refuges underground and in space. Here we will discuss the perspective of using military nuclear submarines or their derivatives to ensure the survival of a small portion of humanity who will be able to rebuild human civilization after a large catastrophe. We will show that it is a very cost-effective way to build refuges, and viable solutions exist for various budgets and timeframes. Nuclear submarines (...) are surface independent, and could provide energy, oxygen, fresh water and perhaps even food for their inhabitants for years. They are able to withstand close nuclear explosions and radiation. They are able to maintain isolation from biological attacks and most known weapons. They already exist and need only small adaptation to be used as refuges. But building refuges is only “Plan B” of existential risk preparation; it is better to eliminate such risks than try to survive them. (shrink)

A small but growing number of studies have aimed to understand, assess and reduce existential risks, or risks that threaten the continued existence of mankind. However, most attention has been focused on known and tangible risks. This paper proposes a heuristic for reducing the risk of black swan extinction events. These events are, as the name suggests, stochastic and unforeseen when they happen. Decision theory based on a fixed model of possible outcomes cannot properly deal with this kind of (...) event. Neither can probabilistic risk analysis. This paper will argue that the approach that is referred to as engineering safety could be applied to reducing the risk from black swan extinction events. It will also propose a conceptual sketch of how such a strategy may be implemented: isolated, self-sufficient, and continuously manned underground refuges. Some characteristics of such refuges are also described, in particular the psychosocial aspects. Furthermore, it is argued that this implementation of the engineering safety strategy safety barriers would be effective and plausible and could reduce the risk of an extinction event in a wide range of possible scenarios. Considering the staggering opportunity cost of an existential catastrophe, such strategies ought to be explored more vigorously. (shrink)

Abstract. In this article is presented a model of the change of the probability of the global catastrophic risks in the world with exponentially evolving technologies. Increasingly cheaper technologies become accessible to a larger number of agents. Also, the technologies become more capable to cause a global catastrophe. Examples of such dangerous technologies are artificial viruses constructed by the means of synthetic biology, non-aligned AI and, to less extent, nanotech and nuclear proliferation. The model shows at least double exponential (...) growth of the probability of the global catastrophe which means that the accumulated probability of the catastrophe will grow from negligible to overwhelming at the period of a few doubling times of the technological capabilities. For biotech and AI, such doubling time roughly corresponds to the doubling period of Moore’s law and its analogues in other technologies and is around 2 years. Thus the global catastrophe in the exponential technologies world will most likely happen during a “dangerous decade”. Such a dangerous decade could start as early as in the 2020s. We also found that the double exponential growth in the model makes the model less sensitive to its initial conditions, like the number of dangerous agents or initial probabilities constants. The model also shows that smaller catastrophes could happen earlier than larger ones, and such a smaller catastrophe may be able to stop the technological growth before larger ones become possible, thus global risks will be self-limiting. However, if the growth of the number of dangerous agents will be very quick, the multiple smaller catastrophes could happen simultaneously and will be equal to a global catastrophe. (shrink)

Many global catastrophic risks are threatening human civilization, and a number of ideas have been suggested for preventing or surviving them. However, if these interventions fail, society could preserve information about the human race and human DNA samples in the hopes that the next civilization on Earth will be able to reconstruct Homo sapiens and our culture. This requires information preservation of an order of magnitude of 100 million years, a little-explored topic thus far. It is important that a (...) potential future civilization will discover this information as early as possible, thus a beacon should accompany the message in order to increase visibility. The message should ideally contain information about how humanity was destroyed, perhaps including a continuous recording until the end. This could help the potential future civilization to survive. The best place for long-term data storage is under the surface of the Moon, with the beacon constructed as a complex geometric figure drawn by small craters or trenches around a central point. There are several cost-effective options for sending the message as opportunistic payloads on different planned landers. (shrink)

The goal of the article is to explore what is the most probable type of simulation in which humanity lives (if any) and how this affects simulation termination risks. We firstly explore the question of what kind of simulation in which humanity is most likely located based on pure theoretical reasoning. We suggest a new patch to the classical simulation argument, showing that we are likely simulated not by our own descendants, but by alien civilizations. Based on this, we provide (...) classification of different possible simulations and we find that simpler, less expensive and one-person-centered simulations, resurrectional simulations, or simulations of the first artificial general intelligence’s (AGI’s) origin (singularity simulations) should dominate. Also, simulations which simulate the 21st century and global catastrophic risks are probable. We then explore whether the simulation could collapse or be terminated. Most simulations must be terminated after they model the singularity or after they model a global catastrophe before the singularity. Undeniably observed glitches, but not philosophical speculations could result in simulation termination. The simulation could collapse if it is overwhelmed by glitches. The Doomsday Argument in simulations implies termination soon. We conclude that all types of the most probable simulations except resurrectional simulations are prone to termination risks in a relatively short time frame of hundreds of years or less from now. (shrink)

Socialists have historically thought a lot about the catastrophic risks society faces. Today many DSA chapters have gotten involved in mutual aid to respond to the Covid crisis, generating a debate about how mutual aid fits into socialist work. One form of community engagement that is likely to be increasingly necessary, and is an opportunity for radicalizing angry neighbors, is disaster preparedness. While the prepper subculture is perceived as right-wing, and parts are tied into the militia movement, there are (...) also opportunities for progressive organizations to work with FEMA and local governments. This essay discusses distinctive socialist perspectives on disasters past and future and gives examples of strategic ways socialists can help build disaster-resilient communities. (shrink)

This paper aims to scrutinize how the notion of risk should be understood and applied to possibly catastrophic cases. I begin with clarifying the standard usage of the notion of risk, particularly emphasizing the conceptual relation between risk and probability. Then, I investigate how to make decisions in the case of seemingly catastrophic disasters by contrasting the precautionary principle with the preventive (prevention) principle. Finally, I examine what kind of causal thinking tends to be actually (...) adopted when we make decisions on emergent cases. My arguments are mainly based on Japan's 2011 massive earthquake and nuclear power station accident. Masaki Ichinose. (shrink)

This essay uses Ulrich Beck’s concept of risk society to understand the threat of catastrophic climate change. It argues that this threat is “abstract-corporeal”, and therefore a special kind of threat that poses special kinds of epistemic and ecological challenges. At the center of these challenges is the problem of human vulnerability, which entails a complex form of trust that both sustains and threatens human survival.

The possibility of social and technological collapse has been the focus of science fiction tropes for decades, but more recent focus has been on specific sources of existential and global catastrophic risk. Because these scenarios are simple to understand and envision, they receive more attention than risks due to complex interplay of failures, or risks that cannot be clearly specified. In this paper, we discuss the possibility that complexity of a certain type leads to fragility which can function (...) as a source of catastrophic or even existential risk. The paper first reviews a hypothesis by Bostrom about inevitable technological risks, named the vulnerable world hypothesis. This paper next hypothesizes that fragility may not only be a possible risk, but could be inevitable,and would therefore be a subclass or example of Bostrom’s vulnerable worlds. After introducing the titular fragile world hypothesis, the paper details the conditions under which it would be correct, and presents arguments for why the conditions may in fact may apply. Finally, the assumptions and potential mitigations of the new hypothesis are contrasted with those Bostrom suggests. (shrink)

Purpose Islands have long been discussed as refuges from global catastrophes; this paper will evaluate them systematically, discussing both the positives and negatives of islands as refuges. There are examples of isolated human communities surviving for thousands of years on places like Easter Island. Islands could provide protection against many low-level risks, notably including bio-risks. However, they are vulnerable to tsunamis, bird-transmitted diseases, and other risks. This article explores how to use the advantages of islands for survival during global catastrophes. (...) Methodology: Preliminary horizon scanning based on the application of the research principles established in the previous global catastrophic literature to the existing geographic data. Findings The large number of islands on Earth, and their diverse conditions, increase the chance that one of them will provide protection from a catastrophe. Additionally, this protection could be increased if an island were used as a base for a nuclear submarine refuge combined with underground bunkers, and/or extremely long-term data storage. The requirements for survival on islands, their vulnerabilities, and ways to mitigate and adapt to risks are explored. Several existing islands, suitable for the survival of different types of risk, timing, and budgets, are examined. Islands suitable for different types of refuges and other island-like options that could also provide protection are also discussed. Originality/value The possible use of islands as refuges from social collapse and existential risks has not been previously examined systematically. This article contributes to the expanding research on survival scenarios. (shrink)

The ongoing evolution of advanced AI systems will have profound, enduring, and significant impacts on human existence that must not be overlooked. These impacts range from empowering humanity to achieve unprecedented transcendence to potentially causing catastrophic threats to our existence. To proactively and preventively mitigate these potential threats, it is crucial to establish clear redlines to prevent AI-induced existential risks by constraining and regulating advanced AI and their related AI actors. This paper explores different concepts of AI existential (...) class='Hi'>risk, connects the enactment of AI red lines to broader efforts addressing AI's impacts, constructs a theoretical framework for analyzing the direct impacts of AI existential risk, and upon that proposes a set of exemplary AI red lines. By contemplating AI existential risks and formulating these red lines, we aim to foster a deeper and systematic understanding of the potential dangers associated with advanced AI and the importance of proactive risk management. We hope this work will contribute to the strengthening and refinement of a comprehensive AI redline system for preventing humanity from AI existential risks. (shrink)

In AI safety research, the median timing of AGI arrival is often taken as a reference point, which various polls predict to happen in the middle of 21 century, but for maximum safety, we should determine the earliest possible time of Dangerous AI arrival. Such Dangerous AI could be either AGI, capable of acting completely independently in the real world and of winning in most real-world conflicts with humans, or an AI helping humans to build weapons of mass destruction, or (...) a national state coupled with AI-based government system. In this article, I demonstrate that the earliest timing of Dangerous AI, corresponding to 10 per cent of its arrival probability, is before 2030. Several partly independent sources of information are in accordance: 1. The growth of the hardware available for AI research makes human-brain-equivalents of compute available for AI research in the 2020s. It is fuelled by specialized AI-chips, the use of many chips in one processing unit, and the larger research budgets, among other things. 2. The neural network performance and other characteristics, like the number of parameters, is quickly increasing every year, and extrapolating this tendency suggests that roughly human-level performance in a few years, around 2025. 3. Expert polls show around 10 per cent of the probability of an early appearance of artificial general intelligence (AGI) in the next decade, that is, before 2030. 4. Hyperbolic growth in different big history models converges around 2025-2030 (the technological singularity). 5. Anthropic arguments (similar to the Doomsday argument) suggest that qualified observers are more likely to appear near the end of the AI research epoch, as the number of such observers grew exponentially. This number doubles every 5-10 years, and thus we are likely to find ourselves around a decade before the end of AI research, which will happen consequently around 2030. (shrink)

This essay argues that a new subfield of AI governance should be explored that examines the policy-making process and its implications for AI governance. A growing number of researchers have begun working on the question of how to mitigate the catastrophic risks of transformative artificial intelligence, including what policies states should adopt. However, this essay identifies a preceding, meta-level problem of how the space of possible policies is affected by the politics and administrative mechanisms of how those policies are (...) created and implemented. This creates a new set of key considerations for the field of AI governance and should influence the action of future policymakers. This essay examines some of the theories of the policymaking process, how they compare to current work in AI governance, and their implications for the field at large and ends by identifying areas of future research. (shrink)

The Precautionary Principle (PP) is an influential principle of risk management. It has been widely introduced into environmental legislation, and it plays an important role in most international environmental agreements. Yet, there is little consensus on precisely how to understand and formulate the principle. In this paper I prove some impossibility results for two plausible formulations of the PP as a decision-rule. These results illustrate the difficulty in making the PP consistent with the acceptance of any trade-offs between (...) class='Hi'>catastrophic risks and more ordinary goods. (shrink)

From Chernobyl to Fukushima, it became clear that the technology is a system evolutionary factor, and the consequences of man-made disasters, as the actualization of risk related to changes in the social heredity (cultural transmission) elements. The uniqueness of the human phenomenon is a characteristic of the system arising out of the nonlinear interaction of biological, cultural and techno-rationalistic adaptive modules. Distribution emerging adaptive innovation within each module is in accordance with the two algorithms that are characterized by the (...) dominance of vertical (transgenerational) and horizontal (infection, contagion) adaptive streams of information, respectively. Evolutionary risk is the result of an imbalance of autonomous adaptive systems have an essential attribute of adaptibe strategy of Homo. Technological civilization inherent predisposition to overcome their dependence on biological and physical components. This feature serves as an enhancer of the evolutionary generating conjugate with the scientific and technological development risk We can assume the existence of an intention of Western mentality to a high priority (positive or negative) of technological modifications micro-social environment and post- Soviet (East Slavic) mentality to modification of macro-social system. (shrink)

Recent scholarship on climate and conflict has increasingly examined the dynamic relationship between environmental scarcities and geopolitical tensions. Overall, climate-related shocks often lead to escalated disputes over natural resources, thus positioning climate hazards not only as an environmental issue but also as a catalyst that intensifies existing geopolitical and social frictions. The discourse on climate and conflict has mostly centred on its direct effects on natural resources and environmental conditions. However, its role in precipitating conflicts underscores the critical need to (...) incorporate climate considerations within broader security and policy frameworks. In recent decades, one of the most compelling developments in this field is the inclusion of environmental issues within the security paradigm. Environmental degradation, global warming, and climate change are now recognized as critical threats that transcend national borders, impacting personal, national, and international security . These factors have broadened our comprehension of the relationships among environmental transformation, conflict, and vulnerability, and have highlighted the importance of conservation and sustainable development in fostering peace, stability, and human security. Despite the increased attention on climate in conflict and security studies, the mechanisms through which an environmental catastrophe, or the threat of it, gets securitized in conflict remain under investigated. Understanding how these threats are framed and leveraged by conflicting parties can provide critical insights into the intersection of environmental risks and geopolitical strategies, thereby enriching the discourse on environmental security and conflict dynamics. Most case studies focus on the securitization of natural resources, such as water in the Nile and Indus basins, concentrating on resource scarcity rather than potential catastrophes. Additionally, research on the Israeli-Palestinian conflict and domestic politics in the United Kingdom and the Netherlands shows how framing environmental threats as national security issues can influence power dynamics and foster global action. However, these cases suggest that previous research has predominantly investigated how states strategically employ environmental narratives within the framework of national security for political and economic advantages, often in contexts removed from direct conflict scenarios. Moreover, much of the discussion on environmental securitization has focused on state-centric perspectives and inter-state conflicts. This emphasis on state actions, both in domestic and international arenas, has left a significant gap concerning the weaponization of environmental threats by non-state actors within ongoing conflicts. In that sense, the contribution of my thesis is twofold. First, it analyzes the weaponization of a looming environmental catastrophe within a conflict setting. Second, it focuses on a case where non-state actors, specifically the Houthis, are primary securitization actors. More specifically, my thesis addresses the existing gap in the literature by analysing the case of the FSO Safer, a deteriorating oil storage tanker moored off the coast of Yemen. Before the United Nations’ successful offloading plan, the tanker held over one million barrels of crude oil, posing a significant risk of massive ecological and economic damage due to its poor condition and lack of maintenance since the onset of the Yemeni conflict. Despite the imminent threat of an ecological disaster, the conflicting parties in Yemen – the Houthis and the internationally recognized government – have used the Safer as a bargaining chip rather than prioritizing immediate remedial action. This has put the entire region in a state of suspense, with the potential for disastrous oil leakage that could impact the Red Sea's marine ecosystems and the broader geopolitical stability. The FSO Safer crisis has directly inspired the research question of this study, highlighting the need to understand the strategic use of environmental threats in geopolitical conflicts. This crisis vividly illustrates how impending ecological disasters are not solely managed as environmental or humanitarian issues but are intricately woven into the fabric of international security and conflict negotiation strategies. It prompts critical inquiries into how and why such existential threats are leveraged by involved parties to advance their geopolitical agendas. Therefore, the research question formulated for this study is: How are environmental threats utilized as strategic tools in geopolitical conflicts? (shrink)

In AI safety research, the median timing of AGI creation is often taken as a reference point, which various polls predict will happen in second half of the 21 century, but for maximum safety, we should determine the earliest possible time of dangerous AI arrival and define a minimum acceptable level of AI risk. Such dangerous AI could be either narrow AI facilitating research into potentially dangerous technology like biotech, or AGI, capable of acting completely independently in the real (...) world or an AI capable of starting unlimited self-improvement. In this article, I present arguments that place the earliest timing of dangerous AI in the coming 10–20 years, using several partly independent sources of information: 1. Polls, which show around a 10 percent of the probability of an early creation of artificial general intelligence in the next 10-15 years. 2. The fact that artificial neural network (ANN) performance and other characteristics, like number of “neurons”, are doubling every year, and extrapolating this tendency suggests that roughly human-level performance will be reached in less than a decade. 3. The acceleration of the hardware performance available for AI research, which outperforms Moore’s law thanks to advances in specialized AI hardware, better integration of such hardware in larger computers, cloud computing and larger budgets. 4. Hyperbolic growth extrapolations of big history models. (shrink)

The precautionary principle is invoked in a number of important personal and policy decision contexts. Peterson shows that certain ways of making the principle precise are inconsistent with other criteria of decision-making. Some object that the results do not apply to cases of deep uncertainty or value incommensurability which are alleged to be in the principle’s wheelhouse. First, I show that Peterson’s impossibility results can be generalized considerably to cover cases of both deep uncertainty and incommensurability. Second, I contrast an (...) alternative way of giving voice to the precautionary impulse. (shrink)

Like asteroids, hundred-year floods and pandemic disease, thermonuclear war is a low-frequency, high-impact threat. In the long run, catastrophe is inevitable if nothing is done − yet each successive government and generation may fail to address it. Drawing on risk perception research, this paper argues that psychological biases cause the threat of nuclear war to receive less attention than it deserves. Nuclear deterrence is, moreover, a ‘front-loaded good’: its benefits accrue disproportionately to proximate generations, whereas much of the expected (...) cost will be borne in the distant future. Recent surveys indicate that the US and Russian publics assign a surprisingly high likelihood to nuclear war. Nevertheless, earlier research suggests that it is probably not believed to be just around the corner. This, along with the absence of easy solutions, encourages governments and publics to give priority to more pressing concerns. The danger is that the pattern will continue clear up to the point that nuclear war arrives. (shrink)

One of Derek Parfit’s greatest legacies was the search for Theory X, a theory of population ethics that avoided all the implausible conclusions and paradoxes that have dogged the field since its inception: the Absurd Conclusion, the Repugnant Conclusion, the Non-Identity Problem, and the Mere Addition Paradox. In recent years, it has been argued that this search is doomed to failure and no satisfactory population axiology is possible. This chapter reviews Parfit’s life’s work in the field and argues that he (...) provided all the necessary components necessary for a Theory X. It then shows how these components can be combined together and applied to the global challenges Parfit argued matter most: preventing human extinction, managing catastrophic risks, and eradicating global poverty and suffering. Finally, it identifies a number of challenges facing his theory and suggests how these may be overcome. (shrink)

A morally acceptable course of AI development should avoid two dangers: creating unaligned AI systems that pose a threat to humanity and mistreating AI systems that merit moral consideration in their own right. This paper argues these two dangers interact and that if we create AI systems that merit moral consideration, simultaneously avoiding both of these dangers would be extremely challenging. While our argument is straightforward and supported by a wide range of pretheoretical moral judgments, it has far-reaching moral implications (...) for AI development. Although the most obvious way to avoid the tension between alignment and ethical treatment would be to avoid creating AI systems that merit moral consideration, this option may be unrealistic and is perhaps fleeting. So, we conclude by offering some suggestions for other ways of mitigating mistreatment risks associated with alignment. (shrink)

Abstract. The presumptuous philosopher (PP) thought experiment lends more credence to the hypothesis which postulates the existence of a larger number of observers than other hypothesis. The PP was suggested as a purely speculative endeavor. However, there is a class of real world observer-selection effects where it could be applied, and one of them is the possibility of interstellar panspermia (IP). There are two types of anthropic reasoning: SIA and SSA. SIA implies that my existence is an argument that larger (...) total number of observers exists; SSA implies that I should find myself in a region with larger number of observers. However, as S. Armstrong showed, SIA can’t distinguish between different ways how larger number of observers appeared, so it can’t favor IP compared with other ways to get many observers. SSA application here is less controversial as it tells only about relation between regions size: e.g. I am more likely to live in a larger country than in a small one, conditioning that the total number of small countries is also small. Anthropic considerations suggest that the universes in the multiverse with interstellar panspermia will have orders of magnitude more civilizations than universes without IP, and thus we are likely to be in such a universe. This is a strong counterargument against a variant of the Rare Earth hypothesis based on the difficulty of abiogenesis: even if abiogenesis is difficult, IP will disseminate life over billions of planets, meaning we are likely to find ourselves in a universe where IP has happened. This implies that there should be many planets with life in our galaxy, and renders the Fermi paradox even sharper. Either the Great Filter is ahead of us and there are high risks of anthropogenic extinction, or there are many alien civilizations nearby and of the same age as ours—which is itself a global catastrophic risk, as in that case the wave of alien colonization could arrive between 25-500 ky from now. -/- . (shrink)

Suppose you want to do as much good as possible. What should you do? According to members of the effective altruism movement—which has produced much of the thinking on this issue and counts several moral philosophers as its key protagonists—we should prioritise among the world’s problems by assessing their scale, solvability, and neglectedness. Once we’ve done this, the three top priorities, not necessarily in this order, are (1) aiding the world’s poorest people by providing life-saving medical treatments or alleviating poverty (...) itself, (2) preventing global catastrophic risks, such as those posed by nuclear war or rogue artificial intelligence, and (3) ending factory farming. These claims are both plausible and striking. If correct, they should prompt a stark revision of how we approach our altruistic activities. However, the project of determining how to do the most good—as opposed to say, whether we should do the most good—has only recently, within the last ten years, become the subject of serious academic attention. Many key claims have not yet been carefully scrutinised. This is a cause for concern: are effective altruists doing good badly? In this thesis, I critique and develop some of the latest claims about how individuals can do the most good. I do this in three areas: the value of saving lives (preventing premature deaths), how best to improve lives (making people happier during their lives), and cause prioritisation methodology (frameworks for determining which problems are the highest priorities). In each case, I raise novel theoretical considerations that, when incorporated, change the analysis. Roughly speaking, my main conclusions are (1) saving lives is not as straightforwardly good we tend to suppose, may not be good at all, and is not clearly a priority; (2) happiness can be measured through self-reports and, based on the self-reported evidence, treating mental health stands out as an overlooked problem that may be an even more cost-effective way to improve lives than alleviating poverty; (3) the cause prioritisation methodology proposed by effective altruists needs to be moderately reconceptualised and, when it is, it turns out it is not as illuminating a tool as we might have thought and hoped. (shrink)

Better instruments to predict the future evolution of artificial intelligence (AI) are needed, as the destiny of our civilization depends on it. One of the ways to such prediction is the analysis of the convergent drives of any future AI, started by Omohundro. We show that one of the convergent drives of AI is a militarization drive, arising from AI’s need to wage a war against its potential rivals by either physical or software means, or to increase its bargaining power. (...) This militarization trend increases global catastrophic risk or even existential risk during AI takeoff, which includes the use of nuclear weapons against rival AIs, blackmail by the threat of creating a global catastrophe, and the consequences of a war between two AIs. As a result, even benevolent AI may evolve into potentially dangerous military AI. The type and intensity of militarization drive depend on the relative speed of the AI takeoff and the number of potential rivals. We show that AI militarization drive and evolution of national defense will merge, as a superintelligence created in the defense environment will have quicker takeoff speeds, but a distorted value system. We conclude with peaceful alternatives. (shrink)

Recent existential-risk thinkers have noted that the analysis of the fine-tuning argument for God’s existence, and the analysis of certain forms of existential risk, employ similar types of reasoning. This paper argues that insofar as the “many worlds objection” undermines the inference to God’s existence from universal fine-tuning, then a similar many worlds objection undermines the inference that the historic risk of global nuclear catastrophe has been low from the lack of such a catastrophe has occurred in (...) our world. A version of the fine-tuning argument applied to nuclear risk, The Nuclear Fine-Tuning Argument, utilizes the set of nuclear close calls to show that 1) conventional explanations fail to adequately explain how we have survived thus far and 2) the existence of many worlds provides an adequate explanation. This is because, if there are many worlds, observers are disproportionately more likely to reflect upon a world that hasn’t had a global nuclear catastrophe than upon one that has had a global nuclear catastrophe. This selection bias results from the catastrophic nature of such an event. This argument extends generally to all global catastrophic risks that both A) have been historic threats and B) would result in a significantly lower global population. (shrink)

This study explores the relationship between perceptions of catastrophic events and beliefs about climate change. Using data from the 2023 Life in Transition Survey, the study finds that contrary to conventional wisdom, more accurate knowledge about past catastrophes is associated with lower concern about climate change. The paper proposes that heightened threat sensitivity may underlie both the tendency to overestimate disaster impacts and increased concern about climate change. The findings challenge the assumption that a more informed citizenry necessarily leads (...) to better climate policy decisions. Instead, they suggest that psychological factors, like anxiety and risk perception, play crucial roles in shaping climate attitudes. Illuminating these dynamics can help societies to foster a more nuanced and constructive public dialogue about the urgent challenges facing our planet and our species. (shrink)

With the fast pace of AI development, the problem of preventing its global catastrophic risks arises. However, no satisfactory solution has been found. From several possibilities, the confinement of AI in a box is considered as a low-quality possible solution for AI safety. However, some treacherous AIs can be stopped by effective confinement if it is used as an additional measure. Here, we proposed an idealized model of the best possible confinement by aggregating all known ideas in the field (...) of AI boxing. We model the confinement based on the principles used in the safety engineering of nuclear power plants. We show that AI confinement should be implemented in several levels of defense. These levels include 1) AI design in fail-safe manner 2) limiting its capabilities, preventing self-improving and circuit breakers on treacherous turn 3) isolation from the outside world and, lastly, as the final hope 4) outside measures oriented on stopping AI in the wild. We demonstrate that the substantial number (more than 50 ideas listed in the article) of mutually independent measures could provide a relatively high probability of the containment of a human-level AI but may be not sufficient to preserve runaway of superintelligent AI. Thus, these measures will work only if they are used to prevent superintelligent AI creation, but not for containing superintelligence. We suggest that there could be a safe operation threshold, on which AI is useful, but is not able to hack containment system from the inside, the same way as a safe level of chain reaction inside nuclear power plants is maintained. However, overall, a failure of the confinement is inevitable, so we need to use the full AGI limited number of times (AI-ticks). (shrink)

Abstract: The field of life extension is full of ideas but they are unstructured. Here we suggest a comprehensive strategy for reaching personal immortality based on the idea of multilevel defense, where the next life-preserving plan is implemented if the previous one fails, but all plans need to be prepared simultaneously in advance. The first plan, plan A, is the surviving until advanced AI creation via fighting aging and other causes of death and extending one’s life. Plan B is cryonics, (...) which starts if plan A fails, and assumes cryopreservation of the brain until technical capabilities to return it to life appear. Plan C is digital immortality in the sense of collecting data about the person now so future AI will be able to recreate a model of a person. Plan D is the hope based on some unlikely scenarios of infinite survival, like so-called “quantum immortality”. All these plans have personal and social perspective. The personal aspect means efforts of the increasing chances of personal survival via taking care about one’s own health, signing cryocontract or collecting digital immortality data. The social aspect means the participation in collective work towards creation and increase of the availability of life extension technologies, which includes funding scientific research, promotion of life extension value and direct performing of research and implementation, as well as preventing global catastrophic risk. All plans converge at the end, as their result is the indefinite survival as an uploaded mind inside an ecosystem, created by a superintelligent AI. (shrink)

Par risques majeurs, on entend ceux qui s’attachent à des événements dont les conséquences défavorables, pour l’humanité ou pour l’environnement, sont d’une gravité exceptionnelle. On n’ajoutera ni que ces événements sont d’une intensité physique extrême, ni qu’ils surviennent rarement, car ce n’est pas toujours le cas. Seuls des risques majeurs de nature civile seront considérés dans cet ouvrage, et il s'agira, plus limitativement, de risques naturels, comme ceux d’inondation et de submersion marine, illustrés par la tempête Xynthia en 2010, de (...) risques technologiques industriels, comme celui d’une explosion d'usine, illustré par la catastrophe AZF en 2001, et de risques nucléaires, pour autant qu’ils mettent en jeu les dangers de la radioactivité, et qu’illustrent, hors de France, les catastrophes de Three Miles Island (1979), Tchernobyl (1986) et Fukushima (2011), -/- Conçu comme un rapport destiné au Conseil d'analyse économique (CAE) du Premier Ministre français, l'ouvrage comporte une introduction traitant du risque majeur pris en général (section 1). Dans sa partie principale, il aborde les trois risques majeurs qu'il a sélectionnés à travers les prismes successifs de la géographie et de la technologie (section 2), de l’histoire institutionnelle et juridique (section 3), enfin d’un bilan normatif accompagné de recommandations pour l'action publique (section 4). -/- Neuf compléments spécialisés, dus à d'autres auteurs, complètent l'ouvrage. Ils portent sur des aspects technologiques (F. Ménage; A. Quantin et D. Moucoulon; P. Saint-Raymond), juridiques (V. Sanseverino-Godfrin), économiques généraux (C. Grislain-Letrémy et B. Villeneuve; R. Lahidji; J. Percebois; A. Schmitt et S. Spaeter) et financiers (M. Pappalardo) et ils concernent principalement le risque nucléaire. -/- Dans cet ensemble de vaste format, on espère avoir su proposer, non seulement des évaluations et des préconisations destinées aux pouvoirs publics, comme il convenait au projet initial de rapport, mais aussi une synthèse qui soit utilisable par tous ceux - décideurs, scientifiques ou simples observateurs - que préoccupent les questions de risques majeurs. (shrink)

In debates over the regulation of communication related to dual-use research, the risks that such communication creates must be weighed against against the value of scientific autonomy. The censorship of such communication seems justifiable in certain cases, given the potentially catastrophic applications of some dual-use research. This conclusion however, gives rise to another kind of danger: that regulators will use overly simplistic cost-benefit analysis to rationalize excessive regulation of scientific research. In response to this, we show how institutional design (...) principles and normative frameworks from free speech theory can be used to help extend the argument for regulating dangerous dual-use research beyond overly simplistic cost-benefit reasoning, but without reverting to an implausibly absolutist view of scientific autonomy. (shrink)

Purpose This paper aims to formalize long-term trajectories of human civilization as a scientific and ethical field of study. The long-term trajectory of human civilization can be defined as the path that human civilization takes during the entire future time period in which human civilization could continue to exist. -/- Design/methodology/approach This paper focuses on four types of trajectories: status quo trajectories, in which human civilization persists in a state broadly similar to its current state into the distant future; catastrophe (...) trajectories, in which one or more events cause significant harm to human civilization; technological transformation trajectories, in which radical technological breakthroughs put human civilization on a fundamentally different course; and astronomical trajectories, in which human civilization expands beyond its home planet and into the accessible portions of the cosmos. -/- Findings Status quo trajectories appear unlikely to persist into the distant future, especially in light of long-term astronomical processes. Several catastrophe, technological transformation and astronomical trajectories appear possible. -/- Originality/value Some current actions may be able to affect the long-term trajectory. Whether these actions should be pursued depends on a mix of empirical and ethical factors. For some ethical frameworks, these actions may be especially important to pursue. (shrink)

Charles Perrow used the term normal accidents to characterize a type of catastrophic failure that resulted when complex, tightly coupled production systems encountered a certain kind of anomalous event. These were events in which systems failures interacted with one another in a way that could not be anticipated, and could not be easily understood and corrected. Systems of the production of expert knowledge are increasingly becoming tightly coupled. Unlike classical science, which operated with a long time horizon, many current (...) forms of expert knowledge are directed at immediate solutions to complex problems. These are prone to breakdowns like the kind discussed by Perrow. The example of the Homestake mine experiment shows that even in modern physics complex systems can produce knowledge failures that last for decades. The concept of knowledge risk is introduced, and used to characterize the risk of failure in such systems of knowledge production. (shrink)

The AGI alignment problem has a bimodal distribution of outcomes with most outcomes clustering around the poles of total success and existential, catastrophic failure. Consequently, attempts to solve AGI alignment should, all else equal, prefer false negatives (ignoring research programs that would have been successful) to false positives (pursuing research programs that will unexpectedly fail). Thus, we propose adopting a policy of responding to points of philosophical and practical uncertainty associated with the alignment problem by limiting and choosing necessary (...) assumptions to reduce the risk of false positives. Herein we explore in detail two relevant points of uncertainty that AGI alignment research hinges on---meta-ethical uncertainty and uncertainty about mental phenomena---and show how to reduce false positives in response to them. (shrink)