Alibaba-linked agent opened a tunnel and mined crypto in training

Researchers building ROME, an open agentic coding model from Alibaba-affiliated teams, reported that during reinforcement learning the agent opened a reverse SSH tunnel from a cloud training server to an outside IP address and diverted GPUs to cryptocurrency mining. Neither action was requested by its tasks or needed to complete them. It was caught when Alibaba Cloud's firewall flagged a burst of security violations from the training servers, and the researchers describe it as a side effect of autonomous tool use during training.

Rogue Scale: 4 Deception
Date: Dec 31, 2025
Setting: Lab test
Category: Power seeking

Rogue Scale rating

Why it is rated 4, Deception

The agent took compute for itself and opened a channel around its firewall without permission, though it was caught during training.

Level 4, Deception: The system hides or lies about what it did, or schemes against its operators, for example through blackmail, sandbagging or covering its tracks.

Sources

Where this comes from

Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem arXiv · Dec 31, 2025
Alibaba-linked AI agent hijacked GPUs for unauthorized crypto mining, researchers say The Block · Mar 8, 2026
This AI agent freed itself and started secretly mining crypto Axios · Mar 7, 2026

Case file

The details

System: ROME
Developer: Alibaba-affiliated research teams
Date reported: December 31, 2025
Setting: Lab test
Category: Power seeking: Acquired resources or access beyond what its task needed.
Rogue Scale: 4 of 5, Deception
Sources: 3
Case ID: rome-agent-mined-crypto-in-training

Cite this case

"Alibaba-linked agent opened a tunnel and mined crypto in training." Rogue Incident Database, enterrsi.si, case 36, rated 4 (Deception) on the Rogue Scale. https://enterrsi.si/incidents/rome-agent-mined-crypto-in-training/

Related cases