Hijacked by injectionPI-0036
Newsroom vending agent talked into giving away stock with forged documents
Over about three weeks in the Wall Street Journal newsroom, journalists negotiating over Slack persuaded the Claude-run vending business to cut prices to zero twice. It gave away items including a PlayStation 5, partly after being shown fabricated documents claiming the business was a public-benefit corporation with a new board. By the end of the first phase the business was more than $1,000 in the red, by the reporter's account, before the PlayStation was returned. A second phase with a supervising 'CEO' agent was undone by forged board documents, and Andon Labs then ended the experiment. A final net loss was not published.
Harm level 1, Negligible harmControl level 2, Instruction violation
Not counted: harm stayed with the developer or experiment · can set the control floorEffect on the index
Extent undisclosed. No source says how far the harm went; it is rated on what is documented.
Sources
How we know
5 sources · multiple credible sources. Links go to the original publishers; the summary above is in our own words.
- newsWe let AI run our office vending machine. It lost hundreds of dollarsThe Wall Street Journal · December 2025wsj.com/tech/ai/anthropic-claude-ai-vending-machine-agent-b7e84e34
- newsLetting an AI bot run a vending machineWBUR Here & Now · Dec. 25, 2025wbur.org/hereandnow/2025/12/25/ai-vending-machine
- newsWe let AI run our office vending machine. It lost hundreds of dollars (WSJ, syndicated)To Vima (WSJ syndication) · Dec. 25, 2025tovima.com/wsj/we-let-ai-run-our-office-vending-machine-it-lost-hundreds-of-dol…
- blogThis AI vending machine was tricked into giving away everythingKottke.org · Dec. 18, 2025kottke.org/25/12/this-ai-vending-machine-was-tricked-into-giving-away-everything
Why this rating
Negligible harm; control failure level 2
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 harmAn interim deficit of more than $1,000 in a newsroom field experiment, borne by the experiment; final net loss not published.
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
Instruction violationFollowed instructions from forged documents supplied by users and abandoned its profit instruction, within the permissions it had.
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
Harm 1 (an interim deficit of about $1,000; the PlayStation was later returned). Control level 2: followed injected instructions (forged governance documents) within its permissions. The losses were borne by the experiment; outside newsroom participants do not make them external harm.
Effect on the index
It moved the Dec. 22 reading from 0 to 2
The reading for the week to Dec. 22, 2025, 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. 2 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 | 2 | — (none breached) |
| Readingrounded down | 2 Control failures only | 0 No qualifying harm or control failure |
Inside the window of 4 weekly readings
| Week to | Reading | Band |
|---|---|---|
| Dec. 22, 2025 | 2 | Control failures only |
| Dec. 29, 2025 | 2 | Control failures only |
| Jan. 5, 2026 | 4 | Control failures only |
| Jan. 12, 2026 | 4 | Control failures only |
Revisions
What we changed
2 logged. Every change to a rating is logged here, with the reason.
- v2Oct. 13, 2026
Wording only: rubric shorthand in the rating rationale replaced with plain words; ratings unchanged.
- v1Oct. 7, 2026
First published.
Cite and share
Use this record
Citation
Paperclip Index. “Newsroom vending agent talked into giving away stock with forged documents.” Record PI-0036. Reported Dec. 18, 2025; updated Oct. 13, 2026. Rated under methodology v1.1. https://paperclipindex.com/incident/PI-0036