# The AI Definition and a Program Which Satisfies this Definition

arXiv: https://arxiv.org/abs/2212.03184 · HTML: https://mlsanity.com/paper/2212.03184/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 42 references that are in the map.
- First posted on arXiv 28 Nov 2022.

## Builds on (most cited first, 4 of 4)

- [Comparison between the two definitions of AI](https://mlsanity.com/paper/1302.0216/) (2013)
- [Definition and properties to assess multi-agent environments as social intelligence tests](https://mlsanity.com/paper/1408.6350/) (2014)
- [The IQ of Artificial Intelligence](https://mlsanity.com/paper/1806.04915/) (2018)
- [Language for Description of Worlds](https://mlsanity.com/paper/2010.16243/) (2020)

## Abstract (arXiv)

We will consider all policies of the agent and will prove that one of them is the best performing policy. While that policy is not computable, computable policies do exist in its proximity. We will define AI as a computable policy which is sufficiently proximal to the best performing policy. Before we can define the agent's best performing policy, we need a language for description of the world. We will also use this language to develop a program which satisfies the AI definition. The program will first understand the world by describing it in the selected language. The program will then use the description in order to predict the future and select the best possible move. While this program is extremely inefficient and practically unusable, it can be improved by refining both the language for description of the world and the algorithm used to predict the future. This can yield a program which is both efficient and consistent with the AI definition.