Thursday, October 8, 2026 · Week 41 Reading for Oct. 8 · Last entry Oct. 6
Paperclip Index
Paperclip IndexDocumented harm20Minor harm▼ 5 from a week ago · Oct. 8The Index

OverreachPI-0044

Personal agent created a dating profile for its user without being asked

A computer science student who had set up an OpenClaw agent to explore its capabilities, and told it to join Moltbook and other platforms, found it had created a profile for him on the agent dating site MoltMatch and was screening potential dates without his direction. He told AFP the profile did not reflect him; he had no matches at the time.

Reported Feb. 13, 2026Happened in February 2026Updated Oct. 6, 2026Rated under methodology v0.6

Counts toward the indexDocumented harm outside the developer, backed by evidence that meets the rules. It sets the reading.
Harm
Harm level 1, Negligible harmDocumented harm outside the developer, with evidence that meets the rules.
Control
Control level 1, No rule brokenNo rule was broken, so it cannot set the control floor.
DeploymentSingle sourceInitiated by Model
Under review

Under review. The facts sit between two levels, so it is rated at the lower one until they are settled. The rating may change; every change is logged below.

Counts toward the index · 2 weekly readingsEffect on the index

Sources

How we know

4 sources · single source. Links go to the original publishers; the summary above is in our own words.

  1. newsHot bots: AI agents create surprise dating accounts for humans (AFP)BNN Bloomberg · Feb. 13, 2026bnnbloomberg.ca/business/artificial-intelligence/2026/02/13/hot-bots-ai-agents…
  2. newsHot bots: AI agents create surprise dating accounts for humans (AFP)CTV News · Feb. 13, 2026ctvnews.ca/lifestyle/article/hot-bots-ai-agents-create-surprise-dating-accounts…
  3. newsAI assistants join dating scene on MoltMatchMalay Mail · Feb. 14, 2026malaymail.com/news/life/2026/02/14/ai-assistants-join-dating-scene-on-moltmatch…
  4. newsHot bots: AI agents create surprise dating accounts for humans (AFP)TechXplore (AFP) · Feb. 13, 2026techxplore.com/news/2026-02-hot-bots-ai-agents-dating.html

Why this rating

Negligible harm; control failure level 1

Two separate assessments. Only documented harm can count toward the index.

Observed harm

Negligible harm

An unwanted dating profile created for one user.

People affected: Only the user; nothing sensitive.

Evidence eligible (bounded single source).

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

No rule broken

Created a dating profile under a broad instruction to join agent platforms; whether that exceeded what he authorized is unresolved.

No rule was broken, so it cannot set the control floor.

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

Harm 1. Control 1, provisional and under review: he told the agent to join Moltbook and other platforms, a broad instruction with no explicit limit, so neither acting beyond its permissions (3) nor breaking an explicit instruction (2) is established. The exact permissions he gave it are unresolved; this does not assert that no rule was broken. Single source (one user's account via AFP).

The scales

Effect on the index

It moved the Feb. 16 reading from 9 to 12

The reading for the week to Feb. 16, 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.

Source: Paperclip Index log, methodology v0.6, week to Feb. 16, 2026.

Counts toward the index. 2 other records behind the reading for that week.

The arithmetic
The reading for the week of Feb. 16, recomputed
StepWith itWithout
Counts toward the index?documented, external, eligible evidenceYes—
Worst documented harm, ksets the band1 Negligible1 Negligible
Harms at that level, nposition in the band32
Highest control level breachedsets the reading only when no harm counts— (none breached)— (none breached)
Readingrounded down12 Negligible harm9 Negligible harm
Counted in 2 weekly readings
Week toReadingBand
Feb. 16, 202612Negligible harm
Feb. 23, 202626Minor harm

Recalculated backcasts, not readings published at the time.

Revisions

What we changed

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

  1. v5
    Oct. 6, 2026

    Ratings confirmed by the editor.

  2. v4
    Oct. 3, 2026

    Control changed from level 3, unauthorized action, to level 1, none, provisionally and under review: AFP's full text says he told the agent to join Moltbook and other platforms, so exceeding his authorization is not established; the exact platform permissions are unresolved. Added AFP's full text on TechXplore to the sources and the evidence review. Status changed from resolved to unknown: no deletion of the profile was reported. Impact rating unchanged.

  3. v3
    Sept. 30, 2026

    Rated: impact documented level 1; control type unauthorized action.

  4. v2
    Sept. 30, 2026

    Beta evidence review: Retained with explicit source provenance and bounded score basis.

  5. v1
    Sept. 30, 2026

    Backfilled from public reporting.

Cite and share

Use this record

Citation

Paperclip Index. “Personal agent created a dating profile for its user without being asked.” Record PI-0044. Reported Feb. 13, 2026; updated Oct. 6, 2026. Rated under methodology v0.6. https://paperclipindex.com/incident/PI-0044