Erik Jenner

Researcher, Google DeepMind

Joined

January 2021

Names

Erik Jenner (Preferred)

Emails

****@gmail.com (Confirmed)

****@berkeley.edu

****@student.uva.nl

****@ejenner.com

****@cs.berkeley.edu

****@google.com

Personal Links

Career & Education History

Researcher

Google DeepMind (google.com)

2025 – Present

PhD student

University of California, Berkeley (berkeley.edu)

2022 – 2025

MS student

University of Amsterdam (uva.nl)

2020 – 2022

Undergrad student

Heidelberg University (uni-heidelberg.de)

2017 – 2020

Advisors, Relations & Conflicts

Project Advisor

Daniel Polani

2019 – 2022

Expertise

No areas of expertise listed

Publications

imitation: Clean Imitation Learning Implementations
Adam Gleave, Mohammad Taufeeque, Juan Rocamonde, Erik Jenner, Steven H Wang, Sam Toyer, Maximilian Ernestus, Nora Belrose, Scott Emmons, Stuart Russell
- OpenReview Archive Direct Upload
- Readers: Everyone
Frontier Models Can Take Actions at Low Probabilities
Alex Serrano, Wen Xing, David Lindner, Erik Jenner
- ICLR 2026 Trustworthy AI
- Readers: Everyone
Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability
Artur Zolkowski, Wen Xing, David Lindner, Florian Tramèr, Erik Jenner
- CoRR 2025
- Readers: Everyone
RL-Obfuscation: Can Language Models Learn to Evade Latent-Space Monitors?
Rohan Gupta, Erik Jenner
- Submitted to ICLR 2026
- Readers: Everyone
Unprobeable Backdoors: Evading Runtime Detection in Transformers
Andis Draguns, Andrew Gritsevskiy, Erik Jenner
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability
Artur Zolkowski, Wen Xing, David Lindner, Florian Tramèr, Erik Jenner
- ICLR 2026 Conference Desk Rejected Submission
- Readers: Everyone
Obfuscated Activations Bypass LLM Latent-Space Defenses
Luke Bailey, Alex Serrano, Abhay Sheshadri, Mikhail Seleznyov, Jordan Taylor, Erik Jenner, Jacob Hilton, Stephen Casper, Carlos Guestrin, Scott Emmons
- ICLR 2026 Poster
- Readers: Everyone
RL-Obfuscation: Can Language Models Learn to Evade Latent-Space Monitors?
Rohan Gupta, Erik Jenner
- Mech Interp Workshop (NeurIPS 2025) Spotlight
- Readers: Everyone
When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors
Scott Emmons, Erik Jenner, David K. Elson, Rif A. Saurous, Senthooran Rajamanoharan, Heng Chen, Irhum Shafkat, Rohin Shah
- CoRR 2025
- Readers: Everyone
Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
Tomek Korbak, Mikita Balesni, Elizabeth Barnes, Yoshua Bengio, Joe Benton, Joseph Bloom, Mark Chen, Alan Cooney, Allan Dafoe, Anca D. Dragan, Scott Emmons, Owain Evans, David Farhi, Ryan Greenblatt, Dan Hendrycks, Marius Hobbhahn, Evan Hubinger, Geoffrey Irving, Erik Jenner, Daniel Kokotajlo et al. (21 additional authors not shown)
- CoRR 2025
- Readers: Everyone

View all 39 publications

Co-Authors

View all 130 co-authors