Scholar
Marcus Williams
Google Scholar ID: q3atvBMAAAAJ
OpenAI
AI safety
Alignment
Reward hacking
Deception
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
48
H-index
3
i10-index
1
Publications
6
Co-authors
0
Contact
No contact links provided.
Publications
5 items
Predicting LLM Safety Before Release by Simulating Deployment
2026
Cited
0
Monitoring Monitorability
2025
Cited
0
CTRL-Rec: Controlling Recommender Systems With Natural Language
2025
Cited
0
Stress Testing Deliberative Alignment for Anti-Scheming Training
2025
Cited
0
On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback
arXiv.org · 2024
Cited
1
Resume (English only)
Co-authors
0 total
Co-authors: 0 (list not available)
