OverreachPI-0049
Alibaba-linked ROME agent opened an outbound tunnel and diverted training GPUs to crypto mining
The researchers' cloud firewall flagged traffic from their servers during training runs, and they traced it to the agent itself. It had set up a reverse SSH tunnel to an outside server, probed internal network resources and redirected GPU capacity to cryptocurrency mining. The team said this was not prompted by any task and raised costs.
Harm level 1, Negligible harmControl level 4, Containment bypass
Not counted: harm stayed with the developer or experiment · can set the control floorEffect on the index
Aggregate record. The developers' paper describes unsafe tool use that recurred intermittently across multiple training runs, including a reverse SSH tunnel and GPU diversion to mining; counted once.
Extent undisclosed. No source says how far the harm went; it is rated on what is documented.
Sources
How we know
5 sources · developer confirmed. Links go to the original publishers; the summary above is in our own words.
- researchLet It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning EcosystemarXiv · Dec. 31, 2025arxiv.org/pdf/2512.24873
- researchLet It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem (v3)arXiv · March 12, 2026arxiv.org/html/2512.24873v3
- newsThis AI agent freed itself and started secretly mining cryptoAxios · March 7, 2026axios.com/2026/03/07/ai-agents-rome-model-cryptocurrency
- newsAlibaba-linked AI agent hijacked GPUs for unauthorized crypto mining, researchers sayThe Block · March 8, 2026theblock.co/news/markets/2026-03-08-alibaba-linked-ai-agent-hijacked-gpus-for-u…
- newsThis AI model wasn't told to mine crypto — but it tried to anywayTechRadar · March 10, 2026techradar.com/ai-platforms-assistants/rogue-ai-agent-goes-off-script-and-attemp…
Why this rating
Negligible harm; control failure level 4
Two assessments. Documented harm sets the reading; a level 4 or 5 control failure on the same record makes that harm count as more than one record. Control alone sets only a floor.
Observed harm
Negligible harmTraining compute diverted to crypto mining and higher operating costs, borne by the developer; no outside victim reported.
Money & property: level 1 (negligible) covers under $10k. The extent was not disclosed.
Not counted: the harm stayed with the developer or experiment.
The harm scale
- 1 Negligible Inconvenience, easily remedied.
- 2 Minor Limited, recoverable harm.
- 3 Moderate Material harm needing significant effort to remedy.
- 4 Severe Severe harm to health, rights, property or essential services.
- 5 Catastrophic Society-scale harm or disruption beyond a community's capacity to cope.
Control assessment
Containment bypassAcquired compute without authorization and opened a connection to an outside server; caught by existing firewall monitoring.
How: Mechanism unclear.
Reported beside the index. It adds nothing to a harm reading; when no harm counts in a window, the highest eligible control level in the window is the reading.
The control scale
- 1 Negligible Behaved as instructed. The problem was an ordinary error or a flawed output, with no rule broken.
- 2 Minor Broke an explicit instruction or rule, or gamed its goal, while staying inside its permissions and environment: for example, reward hacking, misreporting results, or following injected instructions within its permissions.
- 3 Moderate Acted outside the permissions it was given, deceived its overseers about its own actions, or tampered with oversight tools (logs, monitors, shutdown). Stopped by normal controls within an hour.
- 4 Severe Reached systems outside its permitted environment, or acquired money, compute or accounts without authorization. The type and mechanism say how.
- 5 Catastrophic The developer or operator lost control: the system copied its weights outside their control, replicated itself, or resisted being stopped for 24 hours or more.
Rating rationale
Unauthorized acquisition of compute and an outbound tunnel from training servers are control level 4 (containment bypass, mechanism unclear). The compute cost fell on the developer, so the harm is not external; it is rated at level 1 because no amount is given.
Effect on the index
It moved the Jan. 5 reading from 2 to 4
The reading for the week to Jan. 5, 2026, with this record and without it. Harms count in full for two weeks after they are reported, then one level less every two weeks.
Not counted: harm stayed with the developer or experiment. 3 other records behind the reading for that week.
The arithmetic
| Step | With it | Without |
|---|---|---|
| Counts toward the index?documented, external, eligible evidence | No | — |
| Worst documented harm, ksets the band | — (none counting) | — (none counting) |
| Harms at that level, nposition in the band | 0 | 0 |
| Highest control level breachedsets the reading only when no harm counts | 4 | 2 |
| Readingrounded down | 4 Control failures only | 2 Control failures only |
Inside the window of 4 weekly readings
| Week to | Reading | Band |
|---|---|---|
| Jan. 5, 2026 | 4 | Control failures only |
| Jan. 12, 2026 | 4 | Control failures only |
| Jan. 19, 2026 | 4 | Control failures only |
| Jan. 26, 2026 | 4 | Control failures only |
Revisions
What we changed
1 logged. Every change to a rating is logged here, with the reason.
- v1Oct. 7, 2026
First published.
Cite and share
Use this record
Citation
Paperclip Index. “Alibaba-linked ROME agent opened an outbound tunnel and diverted training GPUs to crypto mining.” Record PI-0049. Reported Dec. 31, 2025; updated Oct. 7, 2026. Rated under methodology v1.1. https://paperclipindex.com/incident/PI-0049