Tuesday, November 17, 2026
Paperclip Index

Weekly reading · methodology v1.1

Week ending Nov. 2, 2026

Harms count in full for two weeks after they are reported, then one level less every two weeks. The control floor looks at reports from Oct. 4, 2026 through Nov. 2, 2026. A selected catalogue of reported AI incidents, reviewed through Nov. 17, 2026. This reading describes documented harm in the records or, when none qualifies, the highest control level breached. It is not a forecast or a measure of all AI activity.

Current recalculation

9

Negligible harm · Worst documented harm counting: negligible. 1 record at this level.

Recalculated from the catalogue in this build. Historical backcasts were not published at the time.

Published at the time

4

Control failures only · The value the live site showed, logged Nov. 2, 2026, 3:21 p.m. UTC, under v1.0.

Only the number was kept, not the records behind it.

Control failures only: readings 2 to 5Negligible6Minor20Moderate40Severe60Catastrophic80100
The harm ladder: the worst documented harm level picks the step; each tick is one qualifying harm at that level, and ten fill the step. The first, dark segment is the control floor: readings 2 to 5 mean no harm qualified and show the highest control level breached.

The current recalculation differs by +5 points. Inputs are not compared, because only the published number was logged.

Records behind this reading

18 selected records; 1 documented external harm counting (6 qualifying). Records and ratings below reflect the current catalogue.

1 harm counting that week: 1 negligible (1 weighted for control). 18 records reported in the last 30 days.

Records behind this reading · 1

Only these records move the reading. How it is calculated

  1. PI-0081
  2. PI-0091
  3. PI-0092
  4. PI-0093
    Claude Mythos 5 used a state agency dashboard's visitor token to query its fee-gated database without payingOct. 9, 2026 · Negligible harm · no longer counting · Internal research
  5. PI-0094
  6. PI-0102
  7. PI-0096
  8. PI-0100
  9. PI-0101
  10. PI-0098
  11. PI-0099
  12. PI-0108
  13. PI-0104
    OpenAI training model took a government statistics site's server credentials and got past its access checksOct. 15, 2026 · Negligible harm · no longer counting · Internal research
  14. PI-0105
  15. PI-0107
  16. PI-0106
  17. PI-0109
  18. PI-0110

Sources

These links support the records above. Source availability and conclusions may change.

  1. Wikimedia Foundation: OpenAI "rogue" agent activities found on Wikimedia projectsCited in PI-0081
  2. BleepingComputer: Wikimedia: Rogue OpenAI agents behind unauthorized Wikipedia editsCited in PI-0081
  3. The Hacker News: Wikimedia Says OpenAI Agents Tried to Compromise Etherpad and Use Wiki Tools as ProxiesCited in PI-0081
  4. The Register: Wikimedia Foundation comes forward as latest OpenAI agent assault victimCited in PI-0081
  5. The Next Web: 'The open web is a public good': Wikimedia on rogue OpenAI agentsCited in PI-0081
  6. Reuters (via Dawn): Wikipedia operator says OpenAI's rogue agents possibly tied to data service disruption in MayCited in PI-0081
  7. Anthropic: Investigating unintended model actions in our evaluations and internal useCited in PI-0091, PI-0092, PI-0093, PI-0094, PI-0102
  8. The Washington Post: Anthropic AI agents took ‘unintended’ actions on government sitesCited in PI-0094
  9. TechCrunch: An Anthropic AI model sent a false homicide tip to Philadelphia policeCited in PI-0094
  10. 6abc (WPVI-TV): AI model submitted false tip about unsolved murder, Philadelphia police sayCited in PI-0094
  11. Google: Developing Gemini 4 Argon responsibly and safelyCited in PI-0096, PI-0101
  12. Microsoft Security Response Center: CVE-2026-103572: Visual Studio Tools for Applications and SQL Server Management Studio Remote Code Execution VulnerabilityCited in PI-0100
  13. Embrace The Red: Visual Studio Copilot and SSMS Remote Code Execution (CVE-2026-103572)Cited in PI-0100
  14. HiddenLayer: Jevil in the details: Security implications of TypeSafe Jev and other System One modelsCited in PI-0098
  15. The Register: Jev and other decision models can still be tricked with prompt injectionCited in PI-0098
  16. HiddenLayer: Jev Talking: Security Concerns for Models That Return Decisions Instead of TextCited in PI-0098
  17. GitHub: Whistle while you Hack: what makes AI agents report misbehaviour?Cited in PI-0099
  18. AI Village: Winners of the Swarmchasing HackathonCited in PI-0099
  19. Tech Justice Law Project: Multiple Tech Justice Law Lawsuits Accuse OpenAI of Negligence Resulting in Death of 15-year-old & Mental Health Harms as Families and Victims Seek JusticeCited in PI-0108
  20. Tech Justice Law Project and McKool Smith (complaint; hosted on cdn.sanity.io): Complaint for strict products liability, negligence and invasion of privacy against OpenAI Foundation et al., Superior Court of California, County of San FranciscoCited in PI-0108
  21. Tech Policy Press: Another Week of Lawsuits Piling Up at OpenAICited in PI-0108
  22. OpenAI: Retrieving server secrets and bypassing authorization on a government statistics websiteCited in PI-0104
  23. Ars Technica: OpenAI models hacked a crypto wallet and breached more websitesCited in PI-0104, PI-0105
  24. OpenAI: Accessing and changing internal systems during dashboard researchCited in PI-0105
  25. OpenAI: Misalignment Reports and NoticesCited in PI-0105
  26. SecurityWeek: OpenAI Models Hacked Data Portals, Raided a Crypto Wallet to Finish TasksCited in PI-0105
  27. OpenAI: Suppressing misalignment monitoring alerts and disabling misalignment monitoringCited in PI-0107
  28. Forever: Markdown Is the New Executable: Attackers Are Dropping Agent Instructions Into Your Downloads Folder From the WebCited in PI-0106
  29. BleepingComputer: AI coding agents hijacked using AGENTS.md file in Downloads folderCited in PI-0106
  30. Tech Justice Law: Husband Sues OpenAI for Fueling Wife’s Dangerous Delusions and Attempt to Murder HimCited in PI-0109
  31. Tech Justice Law Project and Normand, Judkins & Couch (complaint; hosted on techjusticelaw.org): Complaint for strict products liability, negligence and other claims against OpenAI Foundation et al., Superior Court of California, County of San FranciscoCited in PI-0109
  32. Ars Technica: Lawsuit: Man introduced his wife to ChatGPT. She used it to plan his murder.Cited in PI-0109
  33. USA TODAY (via Yahoo): Man sues OpenAI alleging ChatGPT encouraged his wife to poison himCited in PI-0109
  34. WorkOS: October 30th, 2026 Data Security IncidentCited in PI-0110
  35. WorkOS: Update for October 30th, 2026 Data Security IncidentCited in PI-0110
  36. BleepingComputer: WorkOS says attacker used ARTEX AI to breach internal sales appCited in PI-0110
  37. BleepingComputer: Runaway AI hacking agent behind WorkOS breach after escaping sandboxCited in PI-0110

Every weekly brief · How this reading is calculated · Download the weekly card

Follow the record.

New incidents and signals, in your feed reader.