10 citations · 21 across the 10 of their papers we have counts for
10 papers
Capabilities Ain't All You Need: Measuring Propensities in AI
Daniel Romero-Alvarado, Fernando Martínez-Plumed, Lorenzo Pacchiardi +11
AI evaluation has primarily focused on measuring capabilities, with formal approaches inspired from Item Response Theory (IRT) being increasingly applied. Yet propensities - the te…
Trust or Check? Understanding the (Evolutionary) Dynamics of User Trust in AI Systems
Adeela Bashir, Zhao Song, Ndidi Bianca Ogbo +21
As the capabilities and adoption of Artificial Intelligence (AI) systems grow, trust in these AI systems is an increasingly urgent concern. Much research has focused on models of A…
Can Media Act as a Soft Regulator of Safe AI Development? A Game Theoretical Analysis
Henrique Correia da Fonseca, António Fernandes, Zhao Song +15
When developers of artificial intelligence (AI) products need to decide between profit and safety for the users, they likely choose profit. Untrustworthy AI technology must come pa…
Do LLMs trust AI regulation? Emerging behaviour of game-theoretic LLM agents
Alessio Buscemi, Daniele Proverbio, Paolo Bova +15
There is general agreement that fostering trust and cooperation within the AI development ecosystem is essential to promote the adoption of trustworthy AI systems. By embedding Lar…
Media and responsible AI governance: a game-theoretic and LLM analysis
Nataliya Balabanova, Adeela Bashir, Paolo Bova +15
This paper investigates the complex interplay between AI developers, regulators, users, and the media in fostering trustworthy AI systems. Using evolutionary game theory and large…
Multi-Agent Risks from Advanced AI
Lewis Hammond, Alan Chan, Jesse Clifton +41
The rapid development of advanced AI agents and the imminent deployment of many instances of these agents will give rise to multi-agent systems of unprecedented complexity. These s…
Quantifying detection rates for dangerous capabilities: a theoretical model of dangerous capability evaluations
Paolo Bova, Alessandro Di Stefano, The Anh Han
We present a quantitative model for tracking dangerous AI capabilities over time. Our goal is to help the policy and research community visualise how dangerous capability testing c…
Trust AI Regulation? Discerning users are vital to build trust and effective AI regulation
Zainab Alalawi, Paolo Bova, Theodor Cimpeanu +8
There is general agreement that some form of regulation is necessary both for AI creators to be incentivised to develop trustworthy systems, and for users to actually trust those s…
Both eyes open: Vigilant Incentives help Regulatory Markets improve AI Safety
Paolo Bova, Alessandro Di Stefano, The Anh Han
In the context of rapid discoveries by leaders in AI, governments must consider how to design regulation that matches the increasing pace of new AI capabilities. Regulatory Markets…
Safe Transformative AI via a Windfall Clause
Paolo Bova, Jonas Emanuel Müller, Benjamin Harack
Society could soon see transformative artificial intelligence (TAI). Models of competition for TAI show firms face strong competitive pressure to deploy TAI systems before they are…