Tag: Academic papers
-
Deep Utopia (Part 1: Monday)
The first lecture of Deep utopia focuses on work, income, and population.
-
Revisiting the shutdown problem (Part 5: Implications)
Suppose that leading arguments for Catastrophic Shutdown Difficulty do not succeed. What follows?
-
Revisiting the shutdown problem (Part 1: Introduction)
The catastrophic shutdown problem is (roughly) the problem of designing AI systems that can be shut down when their acts would lead to existential catastrophe.
-
Instrumental convergence and power-seeking (Part 4: Conclusion)
This post draws lessons from our discussion of instrumental convergence and power-seeking
-
Papers I learned from (Part 6: A timing problem for instrumental convergence)
Should we expect means-end rational agents to preserve their goals? Southan, Ward and Semler are skeptical.
-
Instrumental convergence and power-seeking (Part 1: Introduction)
Power-seeking theorems aim to formally demonstrate that artificial agents are likely to seek power in problematic ways. I argue that leading power-seeking theorems do not succeed.
-
The scope of longtermism (Part 5: A case study – Existential risk)
Many longtermists think that existential risk mitigation escapes the scope-limiting factors. To what extent is this true?
-
The scope of longtermism (Part 4: Unawareness)
Today’s post discusses the final scope-limiting factor: unawareness of relevant acts, states and outcomes
-
The scope of longtermism (Part 2: Rapid diminution)
Rapid diminution occurs when the probabilities of large long-term impacts diminish more quickly than their sizes increase. Rapid diminution tends to shrink the scope of longtermism.