9 citations · 17 across the 8 of their papers we have counts for
8 papers
The Limits of Predicting Agents from Behaviour
Alexis Bellot, Jonathan Richens, Tom Everitt
As the complexity of AI systems and their interactions with the world increases, generating explanations for their behaviour is important for safely deploying AI. For agents, the m…
General agents contain world models
Jonathan Richens, David Abel, Alexis Bellot +1
Are world models a necessary ingredient for flexible, goal-directed behaviour, or is model-free learning sufficient? We provide a formal answer to this question, showing that any a…
Evaluating the Goal-Directedness of Large Language Models
Tom Everitt, Cristina Garbacea, Alexis Bellot +4
To what extent do LLMs use their capabilities towards their given goal? We take this as a measure of their goal-directedness. We evaluate goal-directedness on tasks that require in…
Measuring Goal-Directedness
Matt MacDermott, James Fox, Francesco Belardinelli +1
We define maximum entropy goal-directedness (MEG), a formal measure of goal-directedness in causal models and Markov decision processes, and give algorithms for computing it. Measu…
A Mechanism-Based Approach to Mitigating Harms from Persuasive Generative AI
Seliem El-Sayed, Canfer Akbulut, Amanda McCroskery +17
Recent generative AI systems have demonstrated more advanced persuasive capabilities and are increasingly permeating areas of life where they can influence decision-making. Generat…
The Reasons that Agents Act: Intention and Instrumental Goals
Francis Rhys Ward, Matt MacDermott, Francesco Belardinelli +2
Intention is an important and challenging concept in AI. It is important because it underlies many other concepts we care about, such as agency, manipulation, legal responsibility,…
Robust agents learn causal world models
Jonathan Richens, Tom Everitt
It has long been hypothesised that causal reasoning plays a fundamental role in robust and general intelligence. However, it is not known if agents must learn causal models in orde…
Human Control: Definitions and Algorithms
Ryan Carey, Tom Everitt
How can humans stay in control of advanced artificial intelligence systems? One proposal is corrigibility, which requires the agent to follow the instructions of a human overseer,…