2 citations · 2 across the 19 of their papers we have counts for
13 papers · 1 filter
The Role of Risk Modeling in Advanced AI Risk Management
Chloé Touzet, Henry Papadatos, Malcolm Murray +6
Rapidly advancing artificial intelligence (AI) systems introduce novel, uncertain, and potentially catastrophic risks. Managing these risks requires a mature risk-management infras…
Typed Chain-of-Thought: A Curry-Howard Framework for Verifying LLM Reasoning
Elija Perrier
While Chain-of-Thought (CoT) prompting enhances the reasoning capabilities of large language models, the faithfulness of the generated rationales remains an open problem for model…
Agent Identity Evals: Measuring Agentic Identity
Elija Perrier, Michael Timothy Bennett
Central to agentic capability and trustworthiness of language model agents (LMAs) is the extent they maintain stable, reliable, identity over time. However, LMAs inherit pathologie…
Towards Measurement Theory for Artificial Intelligence
Elija Perrier
We motivate and outline a programme for a formal theory of measurement of artificial intelligence. We argue that formalising measurement for AI will allow researchers, practitioner…
Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack)
Elija Perrier
This position paper argues that formal optimal control theory should be central to AI alignment research, offering a distinct perspective from prevailing AI safety and security app…
Hamiltonian Formalism for Comparing Quantum and Classical Intelligence
Elija Perrier
The prospect of AGI instantiated on quantum substrates motivates the development of mathematical frameworks that enable direct comparison of their operation in classical and quantu…
Quantum AGI: Ontological Foundations
Elija Perrier, Michael Timothy Bennett
We examine the implications of quantum foundations for AGI, focusing on how seminal results such as Bell's theorems (non-locality), the Kochen-Specker theorem (contextuality) and n…
Quantum AIXI: Universal Intelligence via Quantum Information
Elija Perrier
AIXI is a widely studied model of artificial general intelligence (AGI) based upon principles of induction and reinforcement learning. However, AIXI is fundamentally classical in n…
Watts-Per-Intelligence: Part I (Energy Efficiency)
Elija Perrier
We present a mathematical framework for quantifying energy efficiency in intelligent systems by linking energy consumption to information-processing capacity. We introduce a watts-…
Threshold Crossings as Tail Events for Catastrophic AI Risk
Elija Perrier
We analyse circumstances in which bifurcation-driven jumps in AI systems are associated with emergent heavy-tailed outcome distributions. By analysing how a control parameter's ran…
Statistical Scenario Modelling and Lookalike Distributions for Multi-Variate AI Risk
Elija Perrier
Evaluating AI safety requires statistically rigorous methods and risk metrics for understanding how the use of AI affects aggregated risk. However, much AI safety literature focuse…
Position: Stop Acting Like Language Model Agents Are Normal Agents
Elija Perrier, Michael Timothy Bennett
Language Model Agents (LMAs) are increasingly treated as capable of autonomously navigating interactions with humans and tools. Their design and deployment tends to presume they ar…
Infrastructure for AI Agents
Alan Chan, Kevin Wei, Sihao Huang +5
AI agents plan and execute interactions in open-ended environments. For example, OpenAI's Operator can use a web browser to do product comparisons and buy online goods. Much resear…