English
Related papers

Related papers: The Shutdown Problem: An AI Engineering Puzzle for…

200 papers

Is there a way to design powerful AI systems based on machine learning methods that would satisfy probabilistic safety guarantees? With the long-term goal of obtaining a probabilistic guarantee that would apply in every context, we consider…

Artificial Intelligence · Computer Science 2025-06-17 Yoshua Bengio , Michael K. Cohen , Nikolay Malkin , Matt MacDermott , Damiano Fornasiere , Pietro Greiner , Younesse Kaddar

We study secretary problems in settings with multiple agents. In the standard secretary problem, a sequence of arbitrary awards arrive online, in a random order, and a single decision maker makes an immediate and irrevocable decision…

Computer Science and Game Theory · Computer Science 2020-07-15 Tomer Ezra , Michal Feldman , Ron Kupfer

Researchers worried about catastrophic risks from advanced AI have argued that we should expect sufficiently capable AI agents to pursue power over humanity because power is a convergent instrumental goal, something that is useful for a…

Artificial Intelligence · Computer Science 2025-06-10 Christian Tarsney

AI researchers and ethicists have long worried about the threat that automation poses to human dignity, autonomy, and to the sense of personal value that is tied to work. Typically, proposed solutions to this problem focus on ways in which…

Computers and Society · Computer Science 2024-08-20 Emmie Malone , Saleh Afroogh , Jason DCruz , Kush R Varshney

The opaqueness of many complex machine learning algorithms is often mentioned as one of the main obstacles to the ethical development of artificial intelligence (AI). But what does it mean for an algorithm to be opaque? Highly complex…

Machine Learning · Computer Science 2025-08-20 Andrés Páez

With AI systems becoming more powerful and pervasive, there is increasing debate about keeping their actions aligned with the broader goals and needs of humanity. This multi-disciplinary and multi-stakeholder debate must resolve many…

Artificial Intelligence · Computer Science 2021-12-21 Koen Holtman

As Artificial Intelligence (AI) becomes increasingly embedded in financial decision-making, the opacity of complex models presents significant challenges for professionals and regulators. While the field of Explainable AI (XAI) attempts to…

Human-Computer Interaction · Computer Science 2026-02-03 Patricia Marcella Evite , Ekaterina Svetlova , Doina Bucur

We introduce the notion of fault tolerant mechanism design, which extends the standard game theoretic framework of mechanism design to allow for uncertainty about execution. Specifically, we define the problem of task allocation in which…

Computer Science and Game Theory · Computer Science 2013-01-07 Ryan Porter , Amir Ronen , Yoav Shoham , Moshe Tennenholtz

Of primary importance in formulating a response to the increasing prevalence and power of artificial intelligence (AI) applications in society are questions of ontology. Questions such as: What "are" these systems? How are they to be…

Computers and Society · Computer Science 2019-03-11 Scott H. Hawley

The staggering feats of AI systems have brought to attention the topic of AI Alignment: aligning a "superintelligent" AI agent's actions with humanity's interests. Many existing frameworks/algorithms in alignment study the problem on a…

Machine Learning · Computer Science 2024-10-22 Hong Jun Jeon , Benjamin Van Roy

So far, the theory of equilibrium selection in the infinitely repeated prisoner's dilemma is insensitive to communication possibilities. To address this issue, we incorporate the assumption that communication reduces -- but does not…

Theoretical Economics · Economics 2023-04-25 Maximilian Andres

Explanation is necessary for humans to understand and accept decisions made by an AI system when the system's goal is known. It is even more important when the AI system makes decisions in multi-agent environments where the human does not…

In reinforcement learning, agents learn by performing actions and observing their outcomes. Sometimes, it is desirable for a human operator to \textit{interrupt} an agent in order to prevent dangerous situations from happening. Yet, as part…

Artificial Intelligence · Computer Science 2017-05-23 El Mahdi El Mhamdi , Rachid Guerraoui , Hadrien Hendrikx , Alexandre Maurer

People often optimize for long-term goals in collaboration: A mentor or companion doesn't just answer questions, but also scaffolds learning, tracks progress, and prioritizes the other person's growth over immediate results. In contrast,…

Artificial Intelligence · Computer Science 2026-04-08 Grace Liu , Brian Christian , Tsvetomira Dumbalska , Michiel A. Bakker , Rachit Dubey

We position Turing's result regarding the undecidability of the halting problem as a result about programs rather than machines. The mere requirement that a program of a certain kind must solve the halting problem for all programs of that…

Logic in Computer Science · Computer Science 2010-10-19 J. A. Bergstra , C. A. Middelburg

An impossibility theorem demonstrates that a particular problem or set of problems cannot be solved as described in the claim. Such theorems put limits on what is possible to do concerning artificial intelligence, especially the…

Artificial Intelligence · Computer Science 2023-06-19 Mario Brcic , Roman V. Yampolskiy

Large-language-model (LLM)-based AI agents have recently showcased impressive versatility by employing dynamic reasoning, an adaptive, multi-step process that coordinates with external tools. This shift from static, single-turn inference to…

Machine Learning · Computer Science 2026-01-08 Jiin Kim , Byeongjun Shin , Jinha Chung , Minsoo Rhu

This article addresses the societal costs associated with the lack of regulation in Artificial Intelligence and proposes a framework combining innovation and regulation. Over fifty years of AI research, catalyzed by declining computing…

Computers and Society · Computer Science 2025-02-14 Paulo Carvão

The following briefly discusses possible difficulties in communication with and control of an AGI (artificial general intelligence), building upon an explanation of The Fermi Paradox and preceding work on symbol emergence and artificial…

Artificial Intelligence · Computer Science 2024-04-30 Michael Timothy Bennett

As artificial intelligence systems become increasingly agentic, capable of general reasoning, planning, and value prioritization, current safety practices that treat obedience as a proxy for ethical behavior are becoming inadequate. This…

Artificial Intelligence · Computer Science 2025-07-04 Joseph Boland