Three perspectives on corrigibility - shards, simulators, singular learning

This post was first drafted as part of the ML4Good bootcamp.Would it be possible to implement a corrigible agent? Is that likely to happen given current trajectories? Historically, the answer was a resounding "no", but with more recent theories about how LLMs learn, corrigibility now seems possible, if we're careful.DefinitionsFirst, let's define some terms.AgentAn agent chooses actions which modify the state of the world. More formally, we can define a policy function mjx-container[jax="CHTML"]...