collaborators

8 papers

cs.CY2026

Reframing AI Loss of Control: What Control Is, How to Have It, How to Lose It

Ze Shen Chin, Maurice Chiodo, Dennis Müller +1

At present, loss of control risks have gained much prominence in public discussion, particularly in relation to AI, with extensive discourse present among academics, frontier labs,…

cs.CR2026

"We are currently clean on OPSEC": Why JD Can't Encrypt

Maurice Chiodo, Toni Erskine, Dennis Müller +1

We analyse the 2025 Signalgate leak of sensitive US military information by the Trump administration, addressing why confidentiality was violated (messages leaked to the press) in…

cs.CY2026

The Problem of Algorithmic Collisions: Mitigating Unforeseen Risks in a Connected World

Maurice Chiodo, Dennis Müller

The increasing deployment of Artificial Intelligence (AI) and other autonomous algorithmic systems presents the world with new systemic risks. While focus often lies on the functio…

math.HO2025

The Ethical and Sustainable Concerns Triangle: A Framework for Navigating Discourses in Mathematics and Its Education

Dennis Müller, Maurice Chiodo, Michael Meyer

The literature on ethics and sustainability in mathematics and its education is increasingly complex and fragmented, potentially leading to communication breakdowns between differe…

math.HO2025

Ethical and sustainable mathematics is localised: why global paradigms fail and culturally-situated practices are essential

Dennis Müller, Maurice Chiodo

This paper identifies several different interconnected challenges preventing the move towards more ethical and sustainable mathematics education: the entrenched belief in mathemati…

cs.CY2025

Formalising Human-in-the-Loop: Computational Reductions, Failure Modes, and Legal-Moral Responsibility

Maurice Chiodo, Dennis Müller, Paul Siewert +3

We use the notion of oracle machines and reductions from computability theory to formalise different Human-in-the-loop (HITL) setups for AI systems, distinguishing between trivial…