General Purpose Intelligence: Arguing the Orthogonality Thesis

By Stuart Armstrong. 2013

24 citations recorded by the source corpus.

Subfields: Safety, Robustness & Interpretability, Philosophy

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Safety, Robustness & Interpretability

1. Dawn Song
2. Jacob Steinhardt
3. Dan Hendrycks
4. Jerry Zheng Li
5. Steven Basart
6. John Schulman
7. Collin Burns
8. Andrew Critch

In Philosophy

1. Steven Basart
2. Dawn Song
3. Leo Gao
4. Stuart Armstrong
5. Andrew Critch
6. Dan Hendrycks
7. John Schulman
8. Jacob Steinhardt

Citations in the corpus

• Scaling Laws for Reward Model Overoptimization (2022, background): “There are a number of reasons to expect AI misalignment, especially in those more powerful future systems, to occur [Omohundro, 2008, Turner et al., 2021, Armstrong et al., 2013, Hubinger et al., 2019, Soares et al., 2015], and to result in catastrophic outcomes [Carlsmith, 2022, Cotra, 2022].”
• Aligning AI With Shared Human Values (2020, background): “Some contemporary researchers argue machine learning improvements need not lead to ethical AI, as raw intelligence is orthogonal to moral behavior (Armstrong, 2013).”
• Motivated Value Selection for Artificial Agents (2015, background): “But an agent could have any conceivable motivational structure (Bostrom 2012; Armstrong 2013), ignoring the ‘true morality’ even if such a thing existed.”