Sam Adam-Day

Member of Technical Staff

FAR.AI

Sam Adam-Day is a research scientist working in the Deception work stream at FAR.AI.

He previously worked as an independent researcher on a project comparing scalable oversight protocols with Lewis Hammond. Before that he was a postdoctoral research assistant at the Department of Computer Science, University of Oxford, advised by Michael Benedikt.

Sam has a PhD in Mathematics from the University of Oxford, in the area of logic and set theory, supervised by Joel Hamkins and Ehud Hrushovski.

Publications

Not available

News

Scaling Trends for Lie Detector Oversight in Preference Learning

Deception

Scaling the SOLiD lie-detector oversight protocol across Llama and Qwen shows that undetected deception drops as models grow and trusted labelers can be removed, provided the detector's training data covers the fine-tuning distribution.

June 30, 2026
Date Range

Research

Our research explores a portfolio of high-potential agendas.

Events

Our events bring together global leaders in AI.

Programs

Our programs build the field of trustworthy and secure AI