Herbie Bradley
Herbie Bradley
UK AI Safety Institute & University of Cambridge
Verified email at - Homepage
Cited by
Cited by
Pythia: A suite for analyzing large language models across training and scaling
S Biderman, H Schoelkopf, QG Anthony, H Bradley, K O’Brien, E Hallahan, ...
International Conference on Machine Learning, 2397-2430, 2023
Challenges and Applications of Large Language Models
J Kaddour, J Harris, M Mozes, H Bradley, R Raileanu, R McHardy
arXiv preprint arXiv:2307.10169, 2023
Language model crossover: Variation through few-shot prompting
E Meyerson, MJ Nelson, H Bradley, A Gaier, A Moradi, AK Hoover, ...
arXiv preprint arXiv:2302.12170, 2023
Quality-Diversity through AI Feedback
H Bradley, A Dai, H Teufel, J Zhang, K Oostermeijer, M Bellagente, ...
The Twelfth International Conference on Learning Representations (ICLR 2024), 2023
Reclaiming the Digital Commons: A Public Data Trust for Training Data
A Chan, H Bradley, N Rajkumar
AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society 2023, 2023
EleutherAI: Going Beyond" Open Science" to" Science in the Open"
J Phang, H Bradley, L Gao, L Castricato, S Biderman
NeurIPS Workshop on Broadening Research Collaborations 2022, 2022
Diff Models - A New Way to Edit Code
H Bradley, H Fan, H Saini, R Adithyan, S Purohit, J Lehman, 2023
Visibility into AI Agents
A Chan, C Ezell, M Kaufmann, K Wei, L Hammond, H Bradley, E Bluemke, ...
FAccT '24: Proceedings of the 2024 ACM Conference on Fairness …, 2024
The OpenELM Library: Leveraging Progress in Language Models for Novel Evolutionary Algorithms
H Bradley, H Fan, T Galanos, R Zhou, D Scott, J Lehman
Genetic Programming Theory and Practice 20, 2023
Neural MMO 2.0: A Massively Multi-task Addition to Massively Multi-agent Learning
J Suárez, P Isola, KW Choe, D Bloomin, HX Li, N Pinnaparaju, N Kanna, ...
Advances in Neural Information Processing Systems 36 (NeurIPS 2023), 2023
Detecting Backdoors with Meta-Models
L Langosco, N Alex, W Baker, D Quarel, H Bradley, D Krueger
NeurIPS 2023 Workshop on Backdoors in Deep Learning-The Good, the Bad, and …, 2023
Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?
R Schaeffer, H Schoelkopf, B Miranda, G Mukobi, V Madan, A Ibrahim, ...
arXiv preprint arXiv:2406.04391, 2024
Hazards from Increasingly Accessible Fine-Tuning of Downloadable Foundation Models
A Chan, B Bucknall, H Bradley, D Krueger
NeurIPS 2023 Workshop on Socially Responsible Language Modelling Research …, 2023
The NeurIPS 2023 Neural MMO Challenge
J Suárez, P Isola, D Bloomin, KW Choe, HX Li, R Sullivan, N Kanna, ...
Towards Meta-Models for Automated Interpretability
L Langosco, N Alex, W Baker, DJ Quarel, H Bradley, D Krueger
Do LLMs selectively encode the goal of an agent's reach?
L Ruis, A Findeis, H Bradley, HA Rahmani, KW Choe, E Grefenstette, ...
First Workshop on Theory of Mind in Communicating Agents, ICML 2023, 2023
The system can't perform the operation now. Try again later.
Articles 1–16