Obserwuj
Ben Bucknall
Ben Bucknall
DPhil Student, University of Oxford
Zweryfikowany adres z robots.ox.ac.uk
Tytuł
Cytowane przez
Cytowane przez
Rok
Black-box access is insufficient for rigorous ai audits
S Casper, C Ezell, C Siegmann, N Kolt, TL Curtis, B Bucknall, A Haupt, ...
The 2024 ACM Conference on Fairness, Accountability, and Transparency, 2254-2272, 2024
622024
Current and near-term AI as a potential existential risk factor
BS Bucknall, S Dori-Hacohen
Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society, 119-129, 2022
612022
Open-sourcing highly capable foundation models: An evaluation of risks, benefits, and alternative methods for pursuing open-source objectives
E Seger, N Dreksler, R Moulange, E Dardaman, J Schuett, K Wei, ...
arXiv preprint arXiv:2311.09227, 2023
432023
Open Problems in Technical AI Governance
A Reuel, B Bucknall, S Casper, T Fist, L Soder, O Aarne, L Hammond, ...
arXiv preprint arXiv:2407.14981, 2024
27*2024
Towards Publicly Accountable Frontier LLMs: Building an External Scrutiny Ecosystem under the ASPIRE Framework
M Anderljung, ET Smith, J O'Brien, L Soder, B Bucknall, E Bluemke, ...
arXiv preprint arXiv:2311.14711, 2023
23*2023
Structured Access for Third-Party Research on Frontier AI Models: Investigating Researchers' Model Access Requirements
BS Bucknall, RF Trager
162023
Position: Technical Research and Talent is Needed for Effective AI Governance
A Reuel, L Soder, B Bucknall, TA Undheim
Forty-first International Conference on Machine Learning, 2024
7*2024
Hazards from Increasingly Accessible Fine-Tuning of Downloadable Foundation Models
A Chan, B Bucknall, H Bradley, D Krueger
arXiv preprint arXiv:2312.14751, 2023
42023
Open Problems in Machine Unlearning for AI Safety
F Barez, T Fu, A Prabhu, S Casper, A Sanyal, A Bibi, A O'Gara, R Kirk, ...
arXiv preprint arXiv:2501.04952, 2025
12025
Position Paper: Model Access should be a Key Concern in AI Governance
E Kembery, B Bucknall, M Simpson
arXiv preprint arXiv:2412.00836, 2024
2024
Promoting Exploration in Reinforcement Learning through Surprise-Based Intrinsic Motivation
BS Bucknall
2022
Nie można teraz wykonać tej operacji. Spróbuj ponownie później.
Prace 1–11