Erik Jenner
Scholar

Erik Jenner

Google Scholar ID: 8DgF8HcAAAAJ
Google DeepMind
AI SafetyMachine Learning
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
528
 
H-index
9
 
i10-index
8
 
Publications
17
 
Co-authors
8
list available
Contact
Emailerik@ejenner.comTwitterOpen ↗GitHubOpen ↗
Publications
7 items
GDM AI Control Roadmap
2026
Cited
0
Frontier Models Can Take Actions at Low Probabilities
2026
Cited
0
Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability
2025
Cited
0
Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
2025
Cited
0
When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors
2025
Cited
0
RL-Obfuscation: Can Language Models Learn to Evade Latent-Space Monitors?
2025
Cited
0
Obfuscated Activations Bypass LLM Latent-Space Defenses
arXiv.org · 2024
Cited
0
Resume
Academic Achievements
  • Published multiple papers listed on Google Scholar
  • Authored blog posts on the Alignment Forum about early-stage research
  • Introduced the Swoosh activation function (April 2023)
  • Wrote a tutorial on einsum usage in NumPy/PyTorch/TensorFlow (November 2022)
  • Authored a mathematical blog series on Schwartz distributions (March 2022)
Co-authors
6 total
Scott Emmons
Scott Emmons
Google DeepMind
Adam Gleave
Adam Gleave
CEO at FAR AI
Joar Skalse
Joar Skalse
DPhil Student in Computer Science, Oxford University
Maurice Weiler
Maurice Weiler
University of Amsterdam
Herke van Hoof
Herke van Hoof
University of Amsterdam (UVA)
Fred A. Hamprecht
Fred A. Hamprecht
Professor, Heidelberg University