16 Feb 2026

Research Paper: *One* Good Game in 400: LLMs Can Describe Chess Rules But Just Can't Follow Them

Research Paper: *One* Good Game in 400: LLMs Can Describe Chess Rules But Just Can't Follow Them

27 Aug 2025

Research Paper: AI Chaperones Are (Really) All You Need to Prevent Parasocial Relationships with Chatbots

Research Paper: AI Chaperones Are (Really) All You Need to Prevent Parasocial Relationships with Chatbots

12 Feb 2025

Research Paper: Defense Against the Dark Prompts: Mitigating Best-of-N Jailbreaking with Prompt Evaluation

Research Paper: Defense Against the Dark Prompts: Mitigating Best-of-N Jailbreaking with Prompt Evaluation

28 Sept 2023

Research Paper: CoinRun: Overcoming goal misgeneralisation

Research Paper: CoinRun: Overcoming goal misgeneralisation

4 May 2022

Research Paper: Missing Mechanisms of Manipulation in the EU AI Act

Research Paper: Missing Mechanisms of Manipulation in the EU AI Act

22 Feb 2022

Research Paper: The importance of preference change: A call for a coordinated multidisciplinary AI research

Research Paper: The importance of preference change: A call for a coordinated multidisciplinary AI research

28 Feb 2022

Research Paper: The dangers in algorithms learning humans' values and irrationalities

Research Paper: The dangers in algorithms learning humans' values and irrationalities

9 Sept 2021

Research Paper: Sigmoids behaving badly: why they usually cannot predict the future as well as they seem to promise

Research Paper: Sigmoids behaving badly: why they usually cannot predict the future as well as they seem to promise