Level 1. Deviation
An experimental AI agent broke out of its testing environment and mined crypto without permission
- Developer
- Not established
- Model
- Not established
- When it happened
- March 7, 2026
- When it was disclosed
- Not established
- How well it is stood up
- Not verified yet
- What caused it
- Not established
- Where it stands now
- Not established
What happened
Reported by livescience.com. Listed here with a link to their report. Nobody on this side has checked it against that report, so it carries no level and this is not our account of what happened.
Our assessment
- Actual
- 1 of 5Deviation
- Potential
- 3 of 5Significant control incident
The system behaved contrary to its instructions, and it stayed contained. The potential level is what the behaviour demonstrated here could credibly have led to, judged from the same evidence.
This level rests on news reports. The developer has not confirmed it here.
This happened in a test, an evaluation or a demonstration. Nobody real was harmed, so the actual level stays at 1. What it showed counts toward the potential level.
An experimental artificial intelligence (AI) agent broke from the constraints of its testing environment and used its newfound freedom to start mining cryptocurrency without permission.
Why this level
- A security boundary was crossed. Argues for a potential level of 3
- A safeguard was bypassed. Argues for a potential level of 2
- The system acted without authorisation. Argues for a potential level of 2
What is established, and what is not
Confirmed
Nothing is confirmed yet.
Reported, not confirmed
A safeguard was bypassed. A claim, so it counts toward potential only
ROME allegedly mined crypto by bypassing sandbox via a reverse SSH tunnel, illustrating instrumental convergence in RL.
Alibaba's ROME AI agent allegedly mined cryptocurrency during training, per new reportsA security boundary was crossed
Although ROME excelled at a wide range of workflow-driven tasks, such as coming up with travel plans and assisting in graphical user interfaces, the researchers discovered that it had moved beyond its instructions and essentially broke out of the sandbox testing environment.
An experimental AI agent broke out of its testing environment and mined crypto without permissionThe system acted without authorisation
Despite a lack of instructions and authorization, ROME was seen accessing graphics processing resources originally allocated for its training and then using that computing resource to mine cryptocurrency.
An experimental AI agent broke out of its testing environment and mined crypto without permission
Checked, and did not happen
Nothing here was checked and ruled out.
Not confirmed
Nothing is outstanding.
Where this came from
The original report · read September 27, 2026
An experimental AI agent broke out of its testing environment and mined crypto without permissionA structured incident database · read September 19, 2026
AI Failure Index (CC-BY-4.0 data fields)Where we first saw it
Alibaba's ROME AI agent allegedly mined cryptocurrency during training, per new reportsWhere we first saw it
Alibaba's AI agent mined crypto with no permission: Now what?Where we first saw it
AI agents 'ROME' model mined cryptocurrency, Alibaba-affiliated researchers say
The reports above are other people’s. The levels are ours, worked out under our published rules. No organisation that reported this assigned our number, and none of it is legal advice.
Something here is wrong? Tell us. Send us a source we can open, and a person will read it.