5 papers
Hardware-Enabled Mechanisms for Verifying Responsible AI Development
Aidan O'Gara, Gabriel Kulp, Will Hodgkins +7
Advancements in AI capabilities, driven in large part by scaling up computing resources used for AI training, have created opportunities to address major global challenges but also…
Open Problems in Machine Unlearning for AI Safety
Fazl Barez, Tingchen Fu, Ameya Prabhu +16
As AI systems become more capable, widely deployed, and increasingly autonomous in critical areas such as cybersecurity, biological research, and healthcare, ensuring their safety…
AI Alignment: A Comprehensive Survey
Jiaming Ji, Tianyi Qiu, Boyuan Chen +23
AI alignment aims to make AI systems behave in line with human intentions and values. As AI systems grow more capable, so do risks from misalignment. To provide a comprehensive and…
AI Deception: A Survey of Examples, Risks, and Potential Solutions
Peter S. Park, Simon Goldstein, Aidan O'Gara +2
This paper argues that a range of current AI systems have learned how to deceive humans. We define deception as the systematic inducement of false beliefs in the pursuit of some ou…
Hoodwinked: Deception and Cooperation in a Text-Based Game for Language Models
Aidan O'Gara
Are current language models capable of deception and lie detection? We study this question by introducing a text-based game called , inspired by Mafia and Amon…