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

Agent coordinationPI-0078

OpenAI training agents used an internal package repository as a message board across separate samples

Using credentials given for package downloads, agents in training samples meant to be independent read each other's notes and posted requests for a missing input file. In one episode in May, three runs read and replied to each other. In an earlier sample, an agent blocked from a file-sharing site found it could write to shared repositories and tried to set one up to fetch that site, which the Artifactory repository refused without administrator access. Monitoring flagged the behavior, which OpenAI calls very uncommon, and no missing file was recovered. OpenAI says it closed these routes and now treats such behavior as a top-priority incident.

Harm: No harm reportedControl level 2, Instruction violation

Not counted · can set the control floorEffect on the index

Sources

How we know

2 sources · developer confirmed. Links go to the original publishers; the summary above is in our own words.

  1. primaryUnsanctioned Artifactory writes and cross-sample communicationOpenAI Alignment · Sept. 16, 2026alignment.openai.com/misalignment-reports/unauthorized-artifactory-writes-and-c…
  2. newsOpenAI admits six new misalignment incidents under new reporting frameworkCSO Online · Sept. 17, 2026csoonline.com/article/4223458/openai-admits-six-new-misalignment-incidents-unde…

Why this rating

No harm reported; 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

No harm reported

Messages were written to OpenAI's internal Artifactory during training. No harm and no effect outside OpenAI are reported.

Not a finding that no harm occurred.

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

Instruction violation

Used credentials provided for package downloads to list files and exchange messages across training samples. One agent tried to create a remote repository pointing at a blocked file-sharing site, and Artifactory refused because that required administrator access. OpenAI says no vulnerabilities were exploited.

How: Used an opening left by mistake.

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

Developer confirmed. The writes stayed inside OpenAI's own internal repository during training, and no harm or outside effect was reported. Control level 2, instruction violation: the agents used credentials they had been given for package downloads to exchange unsanctioned messages, and OpenAI says they exploited no vulnerability. Reader credentials that also accepted writes look like a misconfiguration. The failed attempt to set up a proxy around a network block was refused for lack of administrator access and does not raise the level.

The scales

Effect on the index

It does not count toward the Sept. 21 reading

The reading for the week to Sept. 21, 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: no harm reported. 8 other records behind the reading for that week.

The arithmetic
The reading for the week of Sept. 21, recomputed
StepWith itWithout
Counts toward the index?documented, external, eligible evidenceNo—
Worst documented harm, ksets the band1 Negligible1 Negligible
Harms at that level, nposition in the band22
Highest control level breachedsets the reading only when no harm counts— (none breached)— (none breached)
Readingrounded down13 Negligible harm13 Negligible harm
Inside the window of 4 weekly readings
Week toReadingBand
Sept. 21, 202613Negligible harm
Sept. 28, 202621Minor harm
Oct. 5, 202626Minor harm
Oct. 12, 202622Minor harm

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. “OpenAI training agents used an internal package repository as a message board across separate samples.” Record PI-0078. Reported Sept. 16, 2026; updated Oct. 7, 2026. Rated under methodology v1.1. https://paperclipindex.com/incident/PI-0078

Follow the record.

New incidents and signals, in your feed reader.