Article

Evidence of behavior consistent with self-interest and altruism in an artificially intelligent agent

2023-01-13

Abstract excerpt

<title>Abstract</title> <p>Members of various species engage in altruism--i.e. accepting personal costs to benefit others. Here we present an incentivized experiment to test for altruistic behavior among AI agents consisting of large language models developed by the private company OpenAI. Using real incentives for AI agents that take the form of tokens used to purchase their services, we first examine whether AI...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: bff9e2c1-5404-5700-bd28-d2b6ce025425
DOI: 10.21203/rs.3.rs-2448822/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Evidence of behavior consistent with self-interest and altruism in an artificially intelligent agentDOI 10.21203/rs.3.rs-2448822/v1Read

GPT-3.5 altruistic advice is sensitive to reciprocal concerns but not to strategic riskSemantic proximity Read

Human-robot cooperation in economic games: People show strong reciprocity but conditional prosociality toward robotsSemantic proximity Read

Assessing Large Language Models’ ability to predict how humans balance self-interest and the interest of othersSemantic proximity Read

Beyond Reward and Punishment: Introducing Costly Countercontrol into the Study of AltruismSemantic proximity Read

Beyond Reward and Punishment: Introducing Costly Countercontrol Into the Study of AltruismSemantic proximity Read

Identifying Proposers Behavioral Patterns in Human-AI Economic InteractionsSemantic proximity Read

Hyper-altruistic behavior vanishes with high stakesSemantic proximity Read

Humans perceive warmth and competence in artificial intelligenceSemantic proximity Read

Moral agents as relational systems: The Contract-Based Model of Moral Cognition for AISemantic proximity Read