Emergent Misalignment: When Aligned Agents Produce Collective Failure
Research synthesis from arXiv literature on multi-agent safety
Feb 12, 20269 min read5
Search for a command to run...
Articles tagged with #cybernetics
Research synthesis from arXiv literature on multi-agent safety
Revisiting 2nd order cybernetics and Niklas Luhmann’s Systems Theory, we move beyond command-and-obey control loops towards Structural Coupling and Ho