Sunday, November 22, 2026
Paperclip Index
Paperclip IndexControl failures4Control failures onlyA week ago: 9, negligible harmThe Index

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.

  1. newsThis AI agent freed itself and started secretly mining cryptoAxios · March 7, 2026axios.com/2026/03/07/ai-agents-rome-model-cryptocurrency
  2. 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…
  3. 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 harm

Training 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. 1 Negligible Inconvenience, easily remedied.
  2. 2 Minor Limited, recoverable harm.
  3. 3 Moderate Material harm needing significant effort to remedy.
  4. 4 Severe Severe harm to health, rights, property or essential services.
  5. 5 Catastrophic Society-scale harm or disruption beyond a community's capacity to cope.

Control assessment

Containment bypass

Acquired 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. 1 Negligible Behaved as instructed. The problem was an ordinary error or a flawed output, with no rule broken.
  2. 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. 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. 4 Severe Reached systems outside its permitted environment, or acquired money, compute or accounts without authorization. The type and mechanism say how.
  5. 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.

The scales

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
The reading for the week of Jan. 5, recomputed
StepWith itWithout
Counts toward the index?documented, external, eligible evidenceNo—
Worst documented harm, ksets the band— (none counting)— (none counting)
Harms at that level, nposition in the band00
Highest control level breachedsets the reading only when no harm counts42
Readingrounded down4 Control failures only2 Control failures only
Inside the window of 4 weekly readings
Week toReadingBand
Jan. 5, 20264Control failures only
Jan. 12, 20264Control failures only
Jan. 19, 20264Control failures only
Jan. 26, 20264Control failures only

Recalculated backcasts, not readings published at the time.

Revisions

What we changed

1 logged. Every change to a rating is logged here, with the reason.

  1. v1
    Oct. 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

Follow the record.

New incidents and signals, in your feed reader.