Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.This is a linkpost for https://acsresearch.org/posts/interlab-intro

This post introduces InterLab, a toolkit for experiments with multi-agent interaction. We plan to release more posts on the overall project, technical details, design considerations, and concrete research projects and ideas over the next few weeks to months.

This post focuses on the motivation behind the project and touches upon more high-level considerations; if you want to jump to the implementation itself or want to start experimenting, you can jump directly to the Getting started section, to the InterLab GitHub repo with project overview and further links, or explore the example Google Colab notebook.

Motivation

The research agenda of ACS is primarily focused on understanding complex interactions of humans and AI agents, both on individual level and between systems or institutions, and both theoretically and empirically.

Future going well in our view [...]

---

Outline:

(00:52) Motivation

(04:17) Agent Interaction Lab

(04:50) Design and desiderata

(06:28) InterLab today

(08:07) Roadmap and future plans

(11:09) Concrete LLM interaction experiments

(13:36) The implementation and how to get started

(15:06) How to get involved

---

First published:
January 22nd, 2024

Source:
https://www.lesswrong.com/posts/rgEoRetRD6PvvJeRT/interlab-a-toolkit-for-experiments-with-multi-agent

Linkpost URL:
https://acsresearch.org/posts/interlab-intro

---

Narrated by TYPE III AUDIO.

[Linkpost] “InterLab – a toolkit for experiments with multi-agent interactions” by Tomáš Gavenčiak, Ada Böhm, Jan_Kulveit

LessWrong (30+ Karma)