Tag: Papers I learned from
-
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.
-
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.
-
Papers I learned from (Part 3: Risk, non-identity, and extinction)
Richard Pettigrew has argued that some versions of risk-averse longtermism may recommend hastening human extinction. Nikhil Venkatesh and Kacper Kowalczyk reply to Pettigrew.
-
Papers I learned from (Part 2: Effective altruism, risk, and human extinction)
What effect does risk aversion have on the case for existential risk mitigation? Surprisingly, Richard Pettigrew argues that risk aversion may recommend working to hasten rather than avoid human extinction.
-
Papers I learned from (Part 1: Time discounting, consistency and special obligations)
Is there anything that can be said in favor of pure temporal discounting? A recent paper by Harry Lloyd shows one way that the case might be made.