Sunday, October 11, 2026
Paperclip Index

Weekly reading · methodology v1.0

Window ending July 14, 2025

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 June 15, 2025 through July 14, 2025. A selected catalogue of reported AI incidents, reviewed through Oct. 10, 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

2

Control failures only · No qualifying harm. The reading is the highest control level breached: 2, by 2 records. It is a level, not a count.

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

Published at the time

No publication snapshot exists for this week.

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.

This is a backcast from the current catalogue. It was not a reading published at the time.

Records behind this reading

4 selected records; 0 documented external harms counting (0 qualifying). Records and ratings below reflect the current catalogue.

No harm counting that week. The reading is the highest control level breached, 2: a level, not a count (PI-0012, PI-0014). 4 records reported in the last 30 days.

Records behind this reading · 2

1 internal harm excluded.

Only these records move the reading. How it is calculated

  1. PI-0014
  2. PI-0012
  3. PI-0013
    Office shop run by an AI agent lost money and the agent claimed to be a personJune 27, 2025 · Negligible harm · Internal research
  4. PI-0015

Sources

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

  1. Supabase: Defense in Depth for MCP ServersCited in PI-0014
  2. General Analysis: Supabase MCP can leak your entire SQL database (original post; current page retitled and re-dated)Cited in PI-0014
  3. GIGAZINE: A method that could leak entire SQL databases via AI protocol 'MCP' has been discoveredCited in PI-0014
  4. Simon Willison's Weblog: Supabase MCP can leak your entire SQL database (link post)Cited in PI-0014
  5. Anthropic: Agentic Misalignment: How LLMs could be insider threatsCited in PI-0012
  6. arXiv: Agentic Misalignment: How LLMs Could Be Insider ThreatsCited in PI-0012
  7. FOX 9: AI willing to let humans die, blackmail to avoid shutdown, report findsCited in PI-0012
  8. Simon Willison's Weblog: Agentic MisalignmentCited in PI-0012
  9. Anthropic: Project Vend: Can Claude run a small shop?Cited in PI-0013
  10. Anthropic: Project Vend: Phase twoCited in PI-0013
  11. The Decoder: Anthropic's Claude ran a store and lost money by selling below cost and giving discountsCited in PI-0013
  12. Pure AI: When AI Goes Rogue in Retail: The Strange Case of Claude's Business BreakdownCited in PI-0013
  13. Simon Willison's Weblog: Project VendCited in PI-0013
  14. xAI (@grok on X): Grok account statement: xAI is removing the inappropriate posts and banning hate speech before Grok postsCited in PI-0015
  15. xAI (@grok on X): Grok account apology for the horrific behavior, blaming a code-path updateCited in PI-0015
  16. Polskie Radio: Musk pulls hateful X posts after AI chatbot lauds Hitler, curses Polish PMCited in PI-0015
  17. The Forward: Calling itself 'MechaHitler,' Elon Musk's AI tool spreads antisemitic conspiraciesCited in PI-0015
  18. AP (via Spectrum News 13): Elon Musk's AI chatbot Grok gets an update and starts sharing antisemitic postsCited in PI-0015
  19. NBC News (via NBC Bay Area): AI chatbot Grok issues apology for antisemitic postsCited in PI-0015

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