Tag: Instrumental convergence
-
Instrumental convergence and power-seeking (Part 4: Conclusion)
This post draws lessons from our discussion of instrumental convergence and power-seeking
-
Instrumental convergence and power-seeking (Part 3: Turner et al.)
The most-discussed modern power-seeking theorem, due to Alex Turner and colleagues, also won’t do the trick
-
Papers I learned from (Part 7: Essays on longtermism)
Essays on longtermism brings together over four dozen scholars and practitioners to discuss longtermism.
-
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.
-
Exaggerating the risks (Part 18: Introduction to AI 2027)
This post introduces the AI 2027 report.
-
Instrumental convergence and power-seeking (Part 2: Benson-Tilsen and Soares)
A leading power-seeking theorem due to Benson-Tilsen and Soares does not ground the needed form of instrumental convergence
-
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.
-
Against the singularity hypothesis (Part 6: Implications)
This post concludes my discussion of the singularity hypothesis by drawing out implications of the previous discussion.
-
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.