Technical Report: Large Language Models can Strategically Deceive their Users when Put Under Pressure
Paper
•
2311.07590
•
Published
•
16
Sam Dornan
SD403
AI & ML interests
Computational Social Science,
Reinforcement Learning,
Agent-Based Models
Recent Activity
updated
a model
about 2 months ago
SD403/rl_course_vizdoom_health_gathering_supreme
updated
a model
about 2 months ago
SD403/ppo-LunarLander-v2-Pytorch
updated
a model
about 2 months ago
SD403/poca-SoccerTwos
Organizations
None yet