# Definitions of intent suitable for algorithms

arXiv: https://arxiv.org/abs/2106.04235 · HTML: https://mlsanity.com/paper/2106.04235/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 122 references that are in the map.
- First posted on arXiv 8 Jun 2021.

## Builds on (most cited first, 6 of 6)

- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Generative Adversarial Networks: An Overview](https://mlsanity.com/paper/1710.07035/) (2017)
- [The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities](https://mlsanity.com/paper/1803.03453/) (2018)
- [Towards Formal Definitions of Blameworthiness, Intention, and Moral Responsibility](https://mlsanity.com/paper/1810.05903/) (2018)
- [Explicability? Legibility? Predictability? Transparency? Privacy? Security? The Emerging Landscape of Interpretable Agent Behavior](https://mlsanity.com/paper/1811.09722/) (2018)
- [Extending counterfactual accounts of intent to include oblique intent](https://mlsanity.com/paper/2106.03684/) (2021)

## Built on by (most cited first, 8 of 8)

- [AI Sandbagging: Language Models can Strategically Underperform on Evaluations](https://mlsanity.com/paper/2406.07358/) (2024)
- [Honesty Is the Best Policy: Defining and Mitigating AI Deception](https://mlsanity.com/paper/2312.01350/) (2023)
- [The Reasons that Agents Act: Intention and Instrumental Goals](https://mlsanity.com/paper/2402.07221/) (2024)
- [Intelligent AI Delegation](https://mlsanity.com/paper/2602.11865/) (2026)
- [Human Control: Definitions and Algorithms](https://mlsanity.com/paper/2305.19861/) (2023)
- [What is Proxy Discrimination?](https://mlsanity.com/paper/2205.05265/) (2022)
- [Experiments with Detecting and Mitigating AI Deception](https://mlsanity.com/paper/2306.14816/) (2023)
- [Evaluating Language Model Character Traits](https://mlsanity.com/paper/2410.04272/) (2024)

## Abstract (arXiv)

Intent modifies an actor's culpability of many types wrongdoing. Autonomous Algorithmic Agents have the capability of causing harm, and whilst their current lack of legal personhood precludes them from committing crimes, it is useful for a number of parties to understand under what type of intentional mode an algorithm might transgress. From the perspective of the creator or owner they would like ensure that their algorithms never intend to cause harm by doing things that would otherwise be labelled criminal if committed by a legal person. Prosecutors might have an interest in understanding whether the actions of an algorithm were internally intended according to a transparent definition of the concept. The presence or absence of intention in the algorithmic agent might inform the court as to the complicity of its owner. This article introduces definitions for direct, oblique (or indirect) and ulterior intent which can be used to test for intent in an algorithmic actor.