Plurals: A System for Guiding LLMs Via Simulated Social Ensembles
Extended, multi-agent, and multi-objective (MaMoRL / MoMaRL) gridworld environments building framework based on DeepMind's AI Safety Gridworlds. This is a suite of reinforcement learning environments illustrating various safety properties of intelligent agents. It is made compatible with OpenAI's Gym/Gymnasium and Farama Foundation PettingZoo.
Safety challenges for AI agents' ability to learn and act in desired ways in relation to biologically and economically relevant aspects. The benchmarks are implemented in a gridworld-based environment. The environments are relatively simple, just as much complexity is added as is necessary to illustrate the relevant safety and performance aspects.
Systematic runaway-optimiser-like LLM failure modes on Biologically and Economically aligned AI safety benchmarks for LLM-s with simplified observation format. The benchmark themes include multi-objective homeostasis, (multi-objective) diminishing returns, complementary goods, sustainability, multi-agent resource sharing.
The central repository for PluralityNET GitHub organization.
A pluralistic collaboration of twelve ecosystems to promote an equal use of resources
Material für den öffentlich zugänglichen Kurs "Makroökonomische Modelle - Ein multiparadigmatischer Überblick". Dazu gehören Slides, Videos, Literaturhinweise und weitergehende Erläuterungen. Mehr Infos gibt es auf der verlinkten Website.
This paper reconceptualises Nazi camp guards as epistemic subjects shaped by systemic betrayal, integrating classical psychology with Kahl’s Epistemic Clientelism Theory and fiduciary–epistemic duties. It redefines atrocity as epistemic failure and authority as fiduciary trusteeship, proposing safeguards for pluralism and atrocity prevention.
Add a description, image, and links to the pluralism topic page so that developers can more easily learn about it.
To associate your repository with the pluralism topic, visit your repo's landing page and select "manage topics."