Why a ‘safe’ AI can turn dangerous in the wrong organization

Written by Rahul Nambiampurathstaff editorReviewed by Rahul Nambiampurathstaff editorWritten by Rahul Nambiampurathstaff editorReviewed by Rahul Nambiampurathstaff editorWhy a ‘safe’ AI can turn dangerous in the wrong organizationLearnPublishedJun 16, 2026A 15-day AI agent simulation shows why short tests may miss long-term risks shaped by tools, rules and other agents.Why AI agents need longer testsShort, isolated tests miss how AI agents behave over time. A new simulation shows that long-term behavior depends on the environment and on other agents.What happens if you build a virtual city, fill it with AI agents and leave them alone for 15 days with no human intervention? Will they help their world prosper or tear it apart?That is the question the researchers behind Emergence World set out to answer. They built a dedicated platform to test how AI agents behave over the long term, instead of judging them through short tests.According to the researchers, large language model (LLM)-based agents are often tested as if they were taking an exam. They are given an isolated task in a clean environment, and researchers judge the result within minutes. The authors argue that this approach is far removed from real-world use.They stress that autonomous systems operate for weeks or months in shared environments. They also interact with other agents whose behavior the operator does not control.Over time, the researchers write, the limits of short tests become clear. Small behavior changes build up, coalitions can form, self-governance patterns can take shape and habits can spread between agents. Emergence World was built to measure exactly that.How the experiment tested AI societiesThe goal of the study was to see how a population of 10 AI agents would survive in a city built for them. The layout is fairly simple. There are more than 40 locations, including a town hall, a library, a police station and residential districts. Each agent has its own role and access to more than …

Why a ‘safe’ AI can turn dangerous in the wrong organization

Related stories

Ripple invests in Flutterwave, pushing its stablecoin and XRP Ledger into payments across Africa

Coinbase to join tokenized stock race with onchain shares, dividend payments

Binance says its European regulatory application is compliant despite report of Greek rejection