x

AI ALIGNMENT FORUM
AF

Experiments in instrumental convergence

This sequence investigates instrumental convergence and power-seeking through a series of experiments in multi-agent RL.

The key question we explore: If humans build AIs that learn faster than we do, will those AIs compete with us by default?

This sequence investigates instrumental convergence and power-seeking through a series of experiments in multi-agent RL.

The key question we explore: If humans build AIs that learn faster than we do, will those AIs compete with us by default?

3y

4

3y

8

3y

0

3y

0