Alex Cloud

According to our database, Alex Cloud authored at least 10 papers between 2015 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Recontextualization Mitigates Specification Gaming without Modifying the Specification.

Ariana Azarbal, Victor Gillioz, Vladimir Ivanov, Bryce Woodworth, Jacob Drori, Nevan Wichers, Aram Ebtekar, Alex Cloud, Alexander Matt Turner

CoRR, December, 2025

Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs.

Igor Shilov, Alex Cloud, Aryo Pradipta Gema, Jacob Goldman-Wetzler, Nina Panickssery, Henry Sleight, Erik Jones, Cem Anil

CoRR, December, 2025

Natural Emergent Misalignment from Reward Hacking in Production RL.

Monte MacDiarmid, Benjamin Wright, Jonathan Uesato, Joe Benton, Jonathan Kutasov, Sara Price, Naia Bouscal, Samuel R. Bowman, Trenton Bricken, Alex Cloud, Carson Denison, Johannes Gasteiger, Ryan Greenblatt, Jan Leike, Jack Lindsey, Vladimir Mikulik, Ethan Perez, Alex Rodrigues, Drake Thomas, Albert Webson, Daniel M. Ziegler, Evan Hubinger

CoRR, November, 2025

Output Supervision Can Obfuscate the Chain of Thought.

Jacob Drori, Luke Marks, Bryce Woodworth, Alex Cloud, Alexander Matt Turner

CoRR, November, 2025

Subliminal Learning: Language models transmit behavioral traits via hidden signals in data.

Alex Cloud, Minh Le, James Chua, Jan Betley, Anna Sztyber-Betley, Jacob Hilton, Samuel Marks, Owain Evans

CoRR, July, 2025

Distillation Robustifies Unlearning.

Bruce W. Lee, Addie Foote, Alex Infanger, Leni Shor, Harish Kamath, Jacob Goldman-Wetzler, Bryce Woodworth, Alex Cloud, Alexander Matt Turner

CoRR, June, 2025

2024

Gradient Routing: Masking Gradients to Localize Computation in Neural Networks.

Alex Cloud, Jacob Goldman-Wetzler, Evzen Wybitul, Joseph Miller, Alexander Matt Turner

CoRR, 2024

2023

Anticipatory Fictitious Play.

Alex Cloud, Albert Wang, Wesley Kerr

Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 2023

2021

Variance Decompositions for Extensive-Form Games.

Alex Cloud, Eric B. Laber

Proceedings of the 2021 IEEE Conference on Games (CoG), 2021

2015

Fast Perfect Simulation of Vervaat Perpetutities.

Alex Cloud, Mark Huber

CoRR, 2015