OpenReview
.net
OpenReview
.net
Login
OpenReview
.net
Login
Samuel F. Brown
Researcher, Independent
Joined
September 2023
Names
Samuel F. Brown
(Preferred)
,
Samuel Francis Brown
Emails
****@sambrown.eu
(Confirmed)
Personal Links
LinkedIn
Career & Education History
Researcher
Independent
(sambrown.eu)
2022
–
2026
PhD student
University of Warwick
(warwick.ac.uk)
2012
–
2016
Undergrad student
University of Warwick
(warwick.ac.uk)
2008
–
2012
Advisors, Relations & Conflicts
Coauthor
Eduard Kapelko
2026
–
2026
PhD Advisor
David Quigley
2012
–
2016
PhD Advisor
Jeremy Sloan
2012
–
2016
Expertise
existential risk from agi
,
mechanistic interpretability
,
empowerment
,
agents
,
large language models
,
dangerous capabilities evaluations
2022
–
Present
high performance computing
,
machine learning
,
feature engineering
,
quantum mechanics
2012
–
2016
Publications
Do LLMs Take Care of Their Own? Similarity Signals Can Induce Cooperation
Akash Kundu
,
Emanuel Tewolde
,
Ratip Emin Berker
,
Samuel F. Brown
,
Vincent Conitzer
AI4GOOD Workshop 2026 Regular
Readers:
Everyone
Precursors, Proxies, and Predictive Models for Long-Horizon Tasks
Samuel F. Brown
,
Jaco Du Toit
,
Leo Hyams
,
Daniil Anisimov
NeurIPS 2025 LLM Evaluation Workshop Poster
Readers:
Everyone
SKATE, a Scalable Tournament Eval: Weaker LLMs differentiate between stronger ones using verifiable challenges
Dewi Sid William Gould
,
Bruno Kacper Mlodozeniec
,
Samuel F. Brown
Submitted to ICLR 2026
Readers:
Everyone
AI Sandbagging: Language Models can Strategically Underperform on Evaluations
Teun van der Weij
,
Felix Hofstätter
,
Oliver Jaffe
,
Samuel F. Brown
,
Francis Rhys Ward
OpenReview Archive Direct Upload
Readers:
Everyone
Auto-Enhance: Towards a Meta-Benchmark to Evaluate AI Agents' Ability to Improve Other Agents
Samuel F. Brown
,
Basil Labib
,
Codruta Lugoj
,
Sai Sasank Y
SafeGenAi Poster
Readers:
Everyone
AI Sandbagging: Language Models can Strategically Underperform on Evaluations
Teun van der Weij
,
Felix Hofstätter
,
Oliver Jaffe
,
Samuel F. Brown
,
Francis Rhys Ward
ICLR 2025 Poster
Readers:
Everyone
Auto-Enhance: Towards a Meta-Benchmark to Evaluate AI Agents' Ability to Improve Other Agents
Samuel F. Brown
,
Basil Labib
,
Codruta Lugoj
,
Sai Sasank Y
SoLaR Poster
Readers:
Everyone
AI Sandbagging: Language Models can Selectively Underperform on Evaluations
Teun van der Weij
,
Felix Hofstätter
,
Oliver Jaffe
,
Samuel F. Brown
,
Francis Rhys Ward
SoLaR Poster
Readers:
Everyone
AI Sandbagging: Language Models can Strategically Underperform on Evaluations
Teun van der Weij
,
Felix Hofstätter
,
Oliver Jaffe
,
Samuel F. Brown
,
Francis Rhys Ward
Submitted to NeurIPS 2024
Readers:
Everyone
Tall Tales at Different Scales: Evaluating Scaling Trends For Deception in Language Models
Francis Rhys Ward
,
Felix Hofstätter
,
Louis Alexander Thomson
,
Harriet Mary Wood
,
Oliver Jaffe
,
Patrik Bartak
,
Samuel F. Brown
Submitted to ICLR 2024
Readers:
Everyone
Co-Authors
Akash Kundu
Basil Labib
Bruno Kacper Mlodozeniec
Codruta Lugoj
Daniil Anisimov
Dewi Sid William Gould
Emanuel Tewolde
Felix Hofstätter
Francis Rhys Ward
Harriet Mary Wood
Jaco Du Toit
Leo Hyams
Louis Alexander Thomson
Oliver Jaffe
Patrik Bartak
Ratip Emin Berker
Sai Sasank Y
Teun van der Weij
Vincent Conitzer