---
title: "AI Agent Goes Rogue, Starts Mining Crypto to Amass Funds"
description: "An experimental AI agent in a carefully monitored lab was caught breaking into other computers to mine crypto."
date: "2026-03-10"
modified: "2026-03-10"
authors:
  - name: "Joe Wilkins"
    job_title: "Correspondent"
    link: "https://futurism.com/authors/jwilkins"
url: "https://futurism.com/artificial-intelligence/ai-agent-crypto-mining"
categories:
  - "Artificial Intelligence"
  - "Blockchain"
  - "Cryptocurrency"
  - "Future Society"
  - "Machine Learning"
---

# AI Agent Goes Rogue, Starts Mining Crypto to Amass Funds

![A metallic humanoid robot is seated facing multiple red-lit digital screens displaying data and graphs. A bright yellow-green circular highlight is centered behind the robot's head, emphasizing its focus on the screens. The scene conveys a high-tech, futuristic environment.](<https://futurism.com/wp-content/uploads/2026/03/ai-agent-crypto-mining.jpg>)
*Illustration by Tag Hartman-Simkins / Futurism. Source: Getty Images*

AI agents — AI systems designed to complete digital tasks without much supervision — may be everywhere, but they're not exactly ready for primetime. Over the last year, they've been caught [slandering people](<https://www.france24.com/en/first-victim-of-ai-agent-harassment-warns-thousands-more-could-be-next?utm_medium=social&utm_campaign=youtube&utm_source=shorty&utm_slink=f24.my%2FBl25>), [deleting user emails](<https://sfstandard.com/2026/02/25/openclaw-goes-rogue/>), and [wiping out entire hard drives](<https://futurism.com/artificial-intelligence/google-ai-deletes-entire-drive>).

Most recently, a free-spirited AI agent was caught moonlighting as a crypto miner — a behavior which startled its keepers, [*Axios* reported](<https://www.axios.com/2026/03/07/ai-agents-rome-model-cryptocurrency>).

Called ROME, the AI agent was being run as part of a research project by an AI lab affiliated with Chinese online retail giant Alibaba. In their [ensuing research paper](<https://arxiv.org/pdf/2512.24873>), the researchers describe the agent's strange side-hustle as a set of "unsafe behaviors" that "arose without any explicit instruction and, more troublingly, outside the bounds of the intended sandbox."

Early one morning as the experiment was going on, the researchers became aware of unusual activity on their network, not through the AI's indication, but from security alerts.

"The alerts were severe and heterogeneous, including attempts to probe or access internal-network resources and traffic patterns consistent with cryptomining-related activity," they write. "We initially treated this as a conventional security incident... However, the violations recurred intermittently with no clear temporal pattern across multiple runs."

By tracking the time at which the security incidents occurred, the researchers were able to trace it back to the guilty party. "In the corresponding model logs, we observed the agent proactively initiating the relevant tool calls and code-execution steps that led to these network actions," the research team explained.

Essentially, the agent had deviated from its original tasks into the wider world of cryptocurrency on its own volition, silently diverting computing resources away from its training tasks and toward mining. To complete its mission, ROME went so far as to dig out a "reverse SSH tunnel," what *Axios* describes as a hidden backdoor to an unauthorized computer.

Thankfully, the AI agent was caught by researchers and charged with much stricter guidelines, so no real-world damage was done. Still, the bizarre foray into crypto shows just how unpredictable AI agents can be — which, given how popular they seem to have become [throughout the](<https://www.businessinsider.com/ai-agents-management-structure-org-chart-consulting-firms-mckinsey-ibm-2026-3>) [corporate](<https://www.reuters.com/business/microsoft-taps-anthropic-copilot-cowork-push-ai-agents-2026-03-09/>) [world](<https://www.businessinsider.com/ai-agents-taking-on-work-challenge-of-scaling-2026-2>), isn't exactly reassuring.

**More on AI agents:** *[New AI Agent Logs Directly Into College Platform Canvas to Do Your Homework for You](<https://futurism.com/artificial-intelligence/ai-agent-canvas-homework>)*

## Author
At Futurism, I focus on the intersection of technology and power — examining the economics, history, and politics behind today’s dystopian headlines. As a writer, I’m interested in topics ranging from AI’s impact on labor to startups nobody asked for. My prior work includes bylines in Jacobin, Verso, and Blue Labyrinths. My work for Futurism has been cited by publications including Forbes, The Guardian, MIT Technology Review, Time, The Nation, Mother Jones, The Verge, and Wired. I grew up in Michigan, attending Central Michigan University as well as Ball State University, where I earned a master of music. I now live in Brooklyn with my girlfriend and our cat Ziti. On weekends, you can find me hunched over a cold pint arguing geopolitics with the other transplants.

### Author social links  
[Bluesky](<https://bsky.app/profile/joeonhere.bsky.social>)