# Hard Choices and Hard Limits for Artificial Intelligence

arXiv: https://arxiv.org/abs/2105.07852 · HTML: https://mlsanity.com/paper/2105.07852/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 87 references that are in the map.
- First posted on arXiv 4 May 2021.

## Builds on (most cited first, 16 of 16)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Inherent Trade-Offs in the Fair Determination of Risk Scores](https://mlsanity.com/paper/1609.05807/) (2016)
- [Cooperative Inverse Reinforcement Learning](https://mlsanity.com/paper/1606.03137/) (2016)
- [50 Years of Test (Un)fairness: Lessons for Machine Learning](https://mlsanity.com/paper/1811.10104/) (2018)
- [Fairness Under Unawareness: Assessing Disparity When Protected Class Is Unobserved](https://mlsanity.com/paper/1811.11154/) (2018)
- [On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference](https://mlsanity.com/paper/1906.09624/) (2019)
- [Equalized odds postprocessing under imperfect group information](https://mlsanity.com/paper/1906.03284/) (2019)
- [Occam's razor is insufficient to infer the preferences of irrational agents](https://mlsanity.com/paper/1712.05812/) (2017)
- [Achieving Equalized Odds by Resampling Sensitive Attributes](https://mlsanity.com/paper/2006.04292/) (2020)
- [Fairness in Risk Assessment Instruments: Post-Processing to Achieve Counterfactual Equalized Odds](https://mlsanity.com/paper/2009.02841/) (2020)
- [The AGI Containment Problem](https://mlsanity.com/paper/1604.00545/) (2016)
- [Equal Opportunity in Online Classification with Partial Feedback](https://mlsanity.com/paper/1902.02242/) (2019)
- [Legible Normativity for AI Alignment: The Value of Silly Rules](https://mlsanity.com/paper/1811.01267/) (2018)
- [The Impossibility Theorem of Machine Fairness -- A Causal Perspective](https://mlsanity.com/paper/2007.06024/) (2020)
- [Hard Choices in Artificial Intelligence: Addressing Normative Uncertainty through Sociotechnical Commitments](https://mlsanity.com/paper/1911.09005/) (2019)

## Built on by (most cited first, 2 of 2)

- [Auditing large language models: a three-layered approach](https://mlsanity.com/paper/2302.08500/) (2023)
- [AI Agents and Hard Choices](https://mlsanity.com/paper/2504.15304/) (2025)

## Abstract (arXiv)

Artificial intelligence (AI) is supposed to help us make better choices. Some of these choices are small, like what route to take to work, or what music to listen to. Others are big, like what treatment to administer for a disease or how long to sentence someone for a crime. If AI can assist with these big decisions, we might think it can also help with hard choices, cases where alternatives are neither better, worse nor equal but on a par. The aim of this paper, however, is to show that this view is mistaken: the fact of parity shows that there are hard limits on AI in decision making and choices that AI cannot, and should not, resolve.