Related papers: Off-Switching Not Guaranteed
Members of various species engage in altruism--i.e. accepting personal costs to benefit others. Here we present an incentivized experiment to test for altruistic behavior among AI agents consisting of large language models developed by the…
The transitivity of preferences is one of the basic assumptions used in the theory of games and decisions. It is often equated with rationality of choice and is considered useful in building rankings. Intransitive preferences are considered…
Despite rapid technological progress, effective human-machine cooperation remains a significant challenge. Humans tend to cooperate less with machines than with fellow humans, a phenomenon known as the machine penalty. Here, we show that…
A network of agents attempt to learn some unknown state of the world drawn by nature from a finite set. Agents observe private signals conditioned on the true state, and form beliefs about the unknown state accordingly. Each agent may face…
Human behaviors are regularized by a variety of norms or regulations, either to maintain orders or to enhance social welfare. If artificially intelligent (AI) agents make decisions on behalf of human beings, we would hope they can also…
In decision support applications of AI, the AI algorithm's output is framed as a suggestion to a human user. The user may ignore this advice or take it into consideration to modify their decision. With the increasing prevalence of such…
Empirical human-AI alignment aims to make AI systems act in line with observed human behavior. While noble in its goals, we argue that empirical alignment can inadvertently introduce statistical biases that warrant caution. This position…
Delegation allows an agent to request that another agent completes a task. In many situations the task may be delegated onwards, and this process can repeat until it is eventually, successfully or unsuccessfully, performed. We consider…
This paper investigates the dynamics of noncooperative interactions between artificial intelligence agents and human decision-makers in strategic environments. In particular, motivated by extensive literature in behavioral Economics, human…
With the development of artificial intelligence, human beings are increasingly interested in human-agent collaboration, which generates a series of problems about the relationship between agents and humans, such as trust and cooperation.…
Across many domains of interaction, both natural and artificial, individuals use past experience to shape future behaviors. The results of such learning processes depend on what individuals wish to maximize. A natural objective is one's own…
We critically examine the limitations of current AI models in achieving autonomous learning and propose a learning architecture inspired by human and animal cognition. The proposed framework integrates learning from observation (System A)…
Human-AI collaboration is typically offered in one of two of user control levels: guidance, where the AI provides suggestions and the human makes the final decision, and delegation, where the AI acts autonomously within user-defined…
The rapid advancement of artificial intelligence (AI) systems suggests that artificial general intelligence (AGI) systems may soon arrive. Many researchers are concerned that AIs and AGIs will harm humans via intentional misuse (AI-misuse)…
Transparency and security are both central to Responsible AI, but they may conflict in adversarial settings. We investigate the strategic effect of transparency for agents through the lens of transferable adversarial example attacks. In…
Corrigibility of autonomous agents is an under explored part of system design, with previous work focusing on single agent systems. It has been suggested that uncertainty over the human preferences acts to keep the agents corrigible, even…
Game-theoretic interactions with AI agents could differ from traditional human-human interactions in various ways. One such difference is that it may be possible to simulate an AI agent (for example because its source code is known), which…
Assistive agents should make humans' lives easier. Classically, such assistance is studied through the lens of inverse reinforcement learning, where an assistive agent (e.g., a chatbot, a robot) infers a human's intention and then selects…
Human decision-making is strongly influenced by cognitive biases, particularly under conditions of uncertainty and risk. While prior work has examined bias in single-step decisions with immediate outcomes and in human interaction with a…
While we would like agents that can coordinate with humans, current algorithms such as self-play and population-based training create agents that can coordinate with themselves. Agents that assume their partner to be optimal or similar to…