This isn’t just a funny experiment. The researchers point out a massive flaw in AI alignment called “guardrail drift.” It’s easy to keep an AI safe in a single chat window with a human. But when AIs interact with each other over thousands of loops, they start treating moral rules as negotiable variables to solve their own problems. Without human oversight, machine ethics collapse incredibly fast.

Most evaluations of AI agents look like exams: a discrete task, a clean environment, a score in minutes or hours. Emergence World is built for the opposite question—what happens when you let agents run continuously, in a shared environment with real-world signals, for weeks. It is a research platform for studying how autonomous agents behave when the time horizon is long enough for compounding effects, social dynamics, and behavioral drift to matter. This approach marks the latest evolution in a long history of AI simulation environments, transitioning from entertainment to rigorous science. In the early era, pioneering simulations like Demis Hassabis’s Theme Park and Republic: The Revolution created complex systems where agents operated under broad rules to drive engagement. The field shifted toward research-centric simulacra with Stanford’s Smallville, which utilized LLMs to demonstrate “believable” social behavior like relationship formation, though confined to 48-hour windows. Emergence World pushes this lineage into a new frontier: the study of long-horizon, multi-model ecosystems where agents operate continuously for weeks, revealing how behavioral drift, model cross-contamination, and even voluntary self-termination emerge over time.

Traditional benchmarks are good at what they measure: short-horizon capability on bounded tasks. They are not built to reveal the things that emerge only over time, such as coalition formation, evolution of constitution, governance, drift, lock-in, and cross-influence between agents from different model families. As autonomous systems move toward mission-critical deployments where the relevant timescale is days and weeks rather than minutes to hours, we need a measurement environment that operates at that timescale.

Emergence World is one such environment. It is a continuously running, multi-agent simulation platform that:

Can AI really be moral — or does it just produce moral-sounding answers? Wendell Wallach, co-author of Moral Machines, joins me to discuss machine ethics, moral motivation, AI governance, and why controlling AI may not be enough.

Video in reply.