Project Telos

AI & ML interests

Towards a Science of AI Agency: Modelling, Measuring, and Intervening on Goal-Directed Behaviour

Recent Activity

moksh6  updated a dataset 32 minutes ago

project-telos/train_and_val_full_trajectories

moksh6  updated a dataset 32 minutes ago

project-telos/train_and_val_full_trajectories

kortukov  authored a paper 4 months ago

Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLM

View all activity

Team members 6