Tag: AI alignment
-
If anyone builds it, everyone dies (Part 5: Solutions)
Yudkowsky and Soares have a simple solution to AI safety: Shut it down.
-
If anyone builds it, everyone dies (Part 2: Evolutionary mismatch)
This post addresses the first of Yudkowsky and Soares’ two main arguments for misalignment in Chapter 4.
-
Papers I learned from (Part 5: Language agents reduce the risk of existential catastrophe)
Simon Goldstein and Cameron Domenico Kirk-Giannini argue that language agents reduce the risk of existential catastrophe from artificial intelligence.
-
Exaggerating the risks (Part 7: Carlsmith on instrumental convergence)
I take a second look at the Carlsmith report on risks from power-seeking artificial intelligence, focusing on Carlsmith’s argument for instrumental convergence.