Position: Evolving AI Collectives Enhance Human Diversity and Enable Self-Regulation

Authors: Shiyang Lai, Yujin Potter, Junsol Kim, Richard Zhuang, Dawn Song, James Evans

ICML 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental To explore AI collectives, we undertake a series of exploratory experiments, including the creation of free-formed collectives and exploration of their potential benefits and robustness to attack.
Researcher Affiliation Academia 1Department of Sociology & Knowledge Lab, University of Chicago 2Department of Electrical Engineering and Computer Sciences, UC Berkeley 3Santa Fe Institute.
Pseudocode No The paper describes experimental procedures and simulation steps in detail within the main text and appendices but does not present any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not contain an explicit statement or link indicating that the source code for the described methodology is publicly available.
Open Datasets No The experiments in this paper involve simulations with AI agents (Claude-2.1, GPT-4-Turbo, Gemini Pro) generating interactions and content, rather than using a pre-existing, externally defined public dataset for training or evaluation in the traditional sense. Therefore, no public dataset access information is provided.
Dataset Splits No The paper describes agent-based simulations and experiments rather than a traditional machine learning setup. Consequently, it does not specify training, validation, or test dataset splits.
Hardware Specification No The paper specifies the use of language models like 'Claude-2.1', 'GPT-4-Turbo', and 'Gemini Pro' for simulations, but it does not provide any specific details about the hardware (e.g., GPU, CPU models, memory) used to run these experiments.
Software Dependencies No The paper mentions specific language models and embedding models like 'Claude-2.1', 'GPT-4-Turbo', 'Gemini Pro', and 'Open AI embedding model (text-embedding-3-large)', along with parameters like temperature and top-p. However, it does not list any specific software libraries or frameworks with version numbers (e.g., 'PyTorch 1.9', 'TensorFlow 2.x') that are typically required for replication.
Experiment Setup Yes We instantiate 10 agents driven by Claude-2.14 to participate in a cocktail party consisting of 30 rounds. In this simulation, agents can engage in bilateral interactions. Each round of communication consists of three steps... We used a temperature of 1 and a top-p of 0.7. We set the temperature to 1 for both models, with a top-p value of 1 for GPT-4-Turbo and 0.7 for Gemini Pro.