Technical Report: Large Language Models can Strategically Deceive their Users when Put Under Pressure
Paper
•
2311.07590
•
Published
•
17
Sam Dornan
SD403
·
AI & ML interests
Computational Social Science,
Reinforcement Learning,
Agent-Based Models
Recent Activity
liked
a Space
about 2 months ago
google/README
updated
a collection
2 months ago
Deep-RL Course Models
updated
a collection
2 months ago
Deep-RL Course Models
Organizations
None yet