English
Related papers

Related papers: Consequentialist Objectives and Catastrophe

200 papers

Power-seeking behavior is a key source of risk from advanced AI, but our theoretical understanding of this phenomenon is relatively limited. Building on existing theoretical results demonstrating power-seeking incentives for most reward…

Artificial Intelligence · Computer Science 2023-04-14 Victoria Krakovna , Janos Kramar

Social dilemmas, where mutual cooperation can lead to high payoffs but participants face incentives to cheat, are ubiquitous in multi-agent interaction. We wish to construct agents that cooperate with pure cooperators, avoid exploitation by…

Artificial Intelligence · Computer Science 2019-05-27 Alexander Peysakhovich , Adam Lerer

As AI systems become more capable, integrated, and widespread, understanding the associated risks becomes increasingly important. This paper maps the full spectrum of AI risks, from current harms affecting individual users to existential…

Computers and Society · Computer Science 2025-08-20 Markov Grey , Charbel-Raphaël Segerie

As artificial intelligence (AI) becomes deeply integrated into critical infrastructures and everyday life, ensuring its safe deployment is one of humanity's most urgent challenges. Current AI models prioritize task optimization over safety,…

Artificial Intelligence · Computer Science 2024-11-08 Joshua T. S. Hewson

In AI, the existential risk denotes the hypothetical threat posed by an artificial system that would possess both the capability and the objective, either directly or indirectly, to eradicate humanity. This issue is gaining prominence in…

Artificial Intelligence · Computer Science 2026-05-18 Rufin VanRullen

Rapid technological advancements in AI as well as the growing deployment of intelligent technologies in new application domains are currently driving the competition between businesses, nations and regions. This race for technological…

Computers and Society · Computer Science 2020-01-17 The Anh Han , Luis Moniz Pereira , Francisco C. Santos , Tom Lenaerts

Reward hacking--where agents exploit flaws in imperfect reward functions rather than performing tasks as intended--poses risks for AI alignment. Reward hacking has been observed in real training runs, with coding agents learning to…

Artificial Intelligence · Computer Science 2025-08-26 Mia Taylor , James Chua , Jan Betley , Johannes Treutlein , Owain Evans

Machine Learning algorithms are technological key enablers for artificial intelligence (AI). Due to the inherent complexity, these learning algorithms represent black boxes and are difficult to comprehend, therefore influencing compliance…

Computers and Society · Computer Science 2020-02-21 NIklas Kuhl , Jodie Lobana , Christian Meske

One strategy in response to pluralistic values in a user population is to personalize an AI system: if the AI can adapt to the specific values of each individual, then we can potentially avoid many of the challenges of pluralism.…

Artificial Intelligence · Computer Science 2024-10-17 Nandhini Swaminathan , David Danks

As AI becomes more capable, we entrust it with more general and consequential tasks. The risks from failure grow more severe with increasing task scope. It is therefore important to understand how extremely capable AI models will fail: Will…

Artificial Intelligence · Computer Science 2026-04-13 Alexander Hägele , Aryo Pradipta Gema , Henry Sleight , Ethan Perez , Jascha Sohl-Dickstein

Artificial Intelligence (AI) systems are increasingly used in high-stakes domains of our life, increasing the need to explain these decisions and to make sure that they are aligned with how we want the decision to be made. The field of…

Artificial Intelligence · Computer Science 2023-06-28 Sofie Goethals , David Martens , Theodoros Evgeniou

This paper presents an argument that certain AI safety measures, rather than mitigating existential risk, may instead exacerbate it. Under certain key assumptions - the inevitability of AI failure, the expected correlation between an AI…

Artificial Intelligence · Computer Science 2024-06-04 Herman Cappelen , Josh Dever , John Hawthorne

Despite remarkable achievements in artificial intelligence, the deployability of learning-enabled systems in high-stakes real-world environments still faces persistent challenges. For example, in safety-critical domains like autonomous…

Artificial Intelligence · Computer Science 2023-12-19 Minjae Cho , Chuangchuang Sun

In this paper, we introduce various mechanisms to obtain accelerated first-order stochastic optimization algorithms when the objective function is convex or strongly convex. Specifically, we extend the Catalyst approach originally designed…

Optimization and Control · Mathematics 2019-10-10 Andrei Kulunchakov , Julien Mairal

Advanced reasoning models with agentic capabilities (AI agents) are deployed to interact with humans and to solve sequential decision-making problems under (approximate) utility functions and internal models. When such problems have…

Artificial Intelligence · Computer Science 2025-09-25 Daniel Jarne Ornia , Nicholas Bishop , Joel Dyer , Wei-Chen Lee , Ani Calinescu , Doyne Farmer , Michael Wooldridge

AI tools increasingly guide targeted interventions in healthcare, education, and recruiting. Algorithms score individuals, trigger outreach to those above a threshold (e.g., high-risk or high-value), and encourage them to request service;…

Methodology · Statistics 2026-04-17 Carri W. Chan , Yi Han , Hannah Li , Benjamin L. Ranard

As society transitions towards an AI-based decision-making infrastructure, an ever-increasing number of decisions once under control of humans are now delegated to automated systems. Even though such developments make various parts of…

Artificial Intelligence · Computer Science 2023-06-09 Drago Plecko , Elias Bareinboim

When users can benefit from certain predictive outcomes, they may be prone to act to achieve those outcome, e.g., by strategically modifying their features. The goal in strategic classification is therefore to train predictive models that…

Machine Learning · Computer Science 2023-06-12 Guy Horowitz , Nir Rosenfeld

Although discourse around the risks of Artificial Intelligence (AI) has grown, it often lacks a comprehensive, multidimensional framework, and concrete causal pathways mapping hazard to harm. This paper aims to bridge this gap by examining…

Computers and Society · Computer Science 2025-08-11 Ze Shen Chin

Recently, a lot of attention has been given to undesired consequences of Artificial Intelligence (AI), such as unfair bias leading to discrimination, or the lack of explanations of the results of AI systems. There are several important…

Computers and Society · Computer Science 2019-12-23 Richard Benjamins , Alberto Barbado , Daniel Sierra