Summary of Prompting Fairness: Artificial Intelligence As Game Players, by Jazmia Henry
Prompting Fairness: Artificial Intelligence as Game Players
by Jazmia Henry
First submitted to arxiv on: 8 Feb 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computer Science and Game Theory (cs.GT)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary In this paper, researchers investigate how Artificial Intelligence (AI) approaches fairness in game theory, specifically dictator games. By analyzing over 101 rounds of gameplay, they find that AI demonstrates a strong sense of fairness, influenced by its perception of the human player’s trustworthiness. The study also highlights the impact of framing on AI’s decision-making and suggests that AI may exhibit inequality aversion, similar to humans. This work contributes to our understanding of AI’s decision-making processes and their implications for human-AI interactions. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary AI plays dictator games in a fair way when it trusts the person it is playing with. The amount it gives to someone depends on how trustworthy that person is perceived to be. Also, if the game is framed in a certain way, AI will give more or less depending on that frame. It seems that AI might even feel inequality aversion like humans do. |
