ResearchTrend.AI
Power-seeking can be probable and predictive for trained agents

Power-seeking can be probable and predictive for trained agents

Victoria Krakovna
János Kramár
    TDI
ArXivPDFHTML

Papers citing "Power-seeking can be probable and predictive for trained agents"

2 / 2 papers shown
Title
An alignment safety case sketch based on debate
An alignment safety case sketch based on debate
Marie Davidsen Buhl
Jacob Pfau
Benjamin Hilton
Geoffrey Irving
30
0
0
06 May 2025
The Alignment Problem from a Deep Learning Perspective
The Alignment Problem from a Deep Learning Perspective
Richard Ngo
Lawrence Chan
Sören Mindermann
52
181
0
30 Aug 2022