Buck Shlegeris
Scholar

Buck Shlegeris

Google Scholar ID: oyDxKw0AAAAJ
CEO, Redwood Research
Deep learningAI safetyAI control
Google Scholar↗
Citations & Impact
All-time
Citations
1,813
 
H-index
14
 
i10-index
18
 
Publications
20
 
Co-authors
0
 
Contact
No contact links provided.
Publications
7 items
Evaluating Control Protocols for Untrusted AI Agents
2025
Cited
0
SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents
2025
Cited
0
Ctrl-Z: Controlling AI Agents via Resampling
2025
Cited
1
How to evaluate control measures for LLM agents? A trajectory from today to superintelligence
2025
Cited
0
A sketch of an AI control safety case
2025
Cited
0
Subversion Strategy Eval: Can language models statelessly strategize to subvert control protocols?
2024
Cited
0
Polysemanticity and Capacity in Neural Networks
arXiv.org · 2022
Cited
23
Resume (English only)
Co-authors
0 total
Co-authors: 0 (list not available)