Three Laws research collaboration
Active
Research focus
• Three Laws is an agentic AI alignment research collaboration investigating how fundamental principles from biology and economics can inform safer, more aligned AI systems.
• Our work centres on homeostasis, multi-objective balancing, sustainability, and universal human values — drawing from nature's time-tested strategies for maintaining equilibrium — to develop benchmarks that elicit and expose dangerous runaway failure modes in current AI approaches.
• We also research frameworks that mitigate these risks. We believe that shifting AI design from "maximise forever" toward "maintain a healthy equilibrium" is a crucial and underexplored part of the alignment solution space.
Open to collaboration
Yes
Looking for
Any collaboration on our research topics
Join the Damaqu community to see this team's full profile.
Papers on Damaqu (9)
- Sets of objectives for a multi-objective RL agent to optimize — LessWrongother
- Client Challengeother
- Why modelling multi-objective homeostasis is essential for AI alignment (and how it helps with AI safety as well). Subtleties and open challenges. — LessWrongother
- Systematic runaway-optimiser-like LLM failure modes on Biologically and Economically aligned AI safety benchmarks for LLMs with simplified observation format (BioBlue) — LessWrongother
- A brief review of the reasons multi-objective RL could be important in AI Safety Research — LessWrongother
- Research agenda for training aligned AIs using concave utility functions following the principles of homeostasis and diminishing returns — LessWrongother
- Open-source LLMs administer maximum electric shocks in a Milgram-like obedience experimentarxiv· 20 May 2026
- BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation formatarxiv· 2 Sept 2025
- From homeostasis to resource sharing: Biologically and economically aligned multi-objective multi-agent gridworld-based AI safety benchmarksarxiv· 30 Sept 2024