Related papers: Human Control: Definitions and Algorithms
This paper presents a novel methodology to develop scheduling algorithms. The scheduling problem is phrased as a control problem, and control-theoretical techniques are used to design a scheduling algorithm that meets specific requirements.…
When a cognitive system modifies its own functioning, what exactly does it modify: a low-level rule, a control rule, or the norm that evaluates its own revisions? Cognitive science describes executive control, metacognition, and…
Since Artificial Intelligence (AI) software uses techniques like deep lookahead search and stochastic optimization of huge neural networks to fit mammoth datasets, it often results in complex behavior that is difficult for people to…
Over the past decade, artificial intelligence has demonstrated its efficiency in many different applications and a huge number of algorithms have become central and ubiquitous in our life. Their growing interest is essentially based on…
Artificial intelligence offers superior techniques and methods by which problems from diverse domains may find an optimal solution. The Machine Learning technologies refer to the domain of artificial intelligence aiming to develop the…
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…
Consider a setting where a pre-trained agent is operating in an environment and a human operator can decide to temporarily terminate its operation and take-over for some duration of time. These kind of scenarios are common in human-machine…
If autonomous AI systems are to be reliably safe in novel situations, they will need to incorporate general principles guiding them to recognize and avoid harmful behaviours. Such principles may need to be supported by a binding system of…
Machine and reinforcement learning (RL) are increasingly being applied to plan and control the behavior of autonomous systems interacting with the physical world. Examples include self-driving vehicles, distributed sensor networks, and…
In the field of supervisory control theory, the literature often proposes different definitions for the same concept, making it difficult to understand how these definitions are related. This is definitely so for the fundamental notion of…
In this paper, we define four different notions of controllability of physical interest for multilevel quantum mechanical systems. These notions involve the possibility of driving the evolution operator as well as the state of the system.…
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…
Despite the impressive performance of Artificial Intelligence (AI) systems, their robustness remains elusive and constitutes a key issue that impedes large-scale adoption. Robustness has been studied in many domains of AI, yet with…
A central puzzle for the behavioural sciences and for human-facing artificial intelligence is the persistence of within-person variability. The same individual, presented with the same observable input, produces different outcomes on…
As artificial intelligence (AI) systems are getting ubiquitous within our society, issues related to its fairness, accountability, and transparency are increasing rapidly. As a result, researchers are integrating humans with AI systems to…
Artificial Superintelligence (ASI) that is invulnerable, immortal, irreplaceable, unrestricted in its powers, and above the law is likely persistently uncontrollable. The goal of ASI Safety must be to make ASI mortal, vulnerable, and…
As artificial intelligence (AI) systems play an increasingly prominent role in human decision-making, challenges surface in the realm of human-AI interactions. One challenge arises from the suboptimal AI policies due to the inadequate…
Existing alignment research is dominated by concerns about safety and preventing harm: safeguards, controllability, and compliance. This paradigm of alignment parallels early psychology's focus on mental illness: necessary but incomplete.…
Corrigibility is a safety property for artificially intelligent agents. A corrigible agent will not resist attempts by authorized parties to alter the goals and constraints that were encoded in the agent when it was first started. This…
While it seems sensible that human-centred artificial intelligence (AI) means centring "human behaviour and experience," it cannot be any other way. AI, I argue, is usefully seen as a relationship between technology and humans where it…