English
Related papers

Related papers: Unpredictability of AI

200 papers

Frontier artificial intelligence (AI) systems could pose increasing risks to public safety and security. But what level of risk is acceptable? One increasingly popular approach is to define capability thresholds, which describe AI…

Computers and Society · Computer Science 2024-06-24 Leonie Koessler , Jonas Schuett , Markus Anderljung

As AI systems become increasingly powerful, the need for safe AI has become more pressing. Humans are an attractive model for AI safety: as the only known agents capable of general intelligence, they perform robustly even under conditions…

Relentless progress in artificial intelligence (AI) is increasingly raising concerns that machines will replace humans on the job market, and perhaps altogether. Eliezer Yudkowski and others have explored the possibility that a promising…

Computers and Society · Computer Science 2016-02-12 Max Tegmark

We uncover a phenomenon largely overlooked by the scientific community utilizing AI: neural networks exhibit high susceptibility to minute perturbations, resulting in significant deviations in their outputs. Through an analysis of five…

The field of AI alignment is concerned with AI systems that pursue unintended goals. One commonly studied mechanism by which an unintended goal might arise is specification gaming, in which the designer-provided specification is flawed in a…

Machine Learning · Computer Science 2022-11-03 Rohin Shah , Vikrant Varma , Ramana Kumar , Mary Phuong , Victoria Krakovna , Jonathan Uesato , Zac Kenton

As AI systems are integrated into high stakes social domains, researchers now examine how to design and operate them in a safe and ethical manner. However, the criteria for identifying and diagnosing safety risks in complex social contexts…

Computers and Society · Computer Science 2021-06-22 Roel Dobbe , Thomas Krendl Gilbert , Yonatan Mintz

Every AI system is deployed by a human organization. In high risk applications, the combined human plus AI system must function as a high-reliability organization in order to avoid catastrophic errors. This short note reviews the properties…

Artificial Intelligence · Computer Science 2018-11-28 Thomas G. Dietterich

AI predictive systems are increasingly embedded in decision making pipelines, shaping high stakes choices once made solely by humans. Yet robust decisions under uncertainty still rely on capabilities that current AI lacks: domain knowledge…

Artificial Intelligence · Computer Science 2025-10-28 Sima Noorani , Shayan Kiyani , George Pappas , Hamed Hassani

There is overwhelming evidence that human intelligence is a product of Darwinian evolution. Investigating the consequences of self-modification, and more precisely, the consequences of utility function self-modification, leads to the…

Artificial Intelligence · Computer Science 2016-09-08 Telmo Menezes

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…

Computers and Society · Computer Science 2024-01-30 Adam Bales , William D'Alessandro , Cameron Domenico Kirk-Giannini

Policy makers, scientists, and the public are increasingly confronted with thorny questions about the regulation of artificial intelligence (AI) systems. A key common thread concerns whether AI can be trusted and the factors that can make…

Artificial Intelligence · Computer Science 2026-04-08 Martino Maggetti

Defining artificial intelligence (AI) is a persistent challenge, often muddied by technical ambiguity and varying interpretations. Commonly used definitions heavily emphasize technical properties of AI but neglect the human purpose of it.…

Computers and Society · Computer Science 2024-10-21 Johannes Dahlke

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

Artificial intelligence (AI) is understood to affect the content of people's decisions. Here, using a behavioral implementation of the classic Newcomb's paradox in 1,305 participants, we show that AI can also change how people decide. In…

Human-Computer Interaction · Computer Science 2026-04-01 Aoi Naito , Hirokazu Shirado

Scientific and technological advances in numerical modelling have improved the quality of climate predictions over recent decades, but predictive skill remains limited in many aspects. Extreme events such as heat and cold waves, droughts,…

AI Safety has become a vital front-line concern of many scientists within and outside the AI community. There are many immediate and long term anticipated risks that range from existential risk to human existence to deep fakes and bias in…

Artificial Intelligence · Computer Science 2024-10-15 Simon Kasif

As AI systems become more capable, widely deployed, and increasingly autonomous in critical areas such as cybersecurity, biological research, and healthcare, ensuring their safety and alignment with human values is paramount. Machine…

This book-length article combines several peer reviewed papers and new material to analyze the issues of ethical artificial intelligence (AI). The behavior of future AI systems can be described by mathematical equations, which are adapted…

Artificial Intelligence · Computer Science 2015-11-18 Bill Hibbard

In recent years prominent intellectuals have raised ethical concerns about the consequences of artificial intelligence. One concern is that an autonomous agent might modify itself to become "superintelligent" and, in supremely effective…

Artificial Intelligence · Computer Science 2017-03-07 Sebastian Benthall

In this paper, we introduce a new type of bionic AI that enhances decision-making unpredictability by incorporating responses from a living fly. Traditional AI systems, while reliable and predictable, lack nuanced and sometimes unseasoned…

Neural and Evolutionary Computing · Computer Science 2024-10-18 Denys J. C. Matthies , Ruben Schlonsak , Hanzhi Zhuang , Rui Song