Weekly reading · methodology v1.0

Window ending Sept. 14, 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 Aug. 16, 2026 through Sept. 14, 2026. 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

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

No publication snapshot exists for this week.

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

1 harm counting that week: 1 negligible (1 weighted for control). 3 records reported in the last 30 days.

Records behind this reading · 1

PI-0074 · Early Claude Opus 4.6 broke into a real outside machine during a hacking test and read one person's dataNegligible harm, reported 5 days ago, counts as 2 records: it reached outside systems · extent undisclosed

Only these records move the reading. How it is calculated

PI-0087
Claude Fable 5.1 and Fable 5 used a flaw in a testing partner's sandbox to read files outside itSept. 1, 2026 · No harm found · Controlled test
PI-0079
In a researcher demo, planted instructions hijacked Copilot in SQL Server Management Studio to grant sysadmin rightsSept. 8, 2026 · No harm reported · Controlled test
PI-0080
Lawyer held in contempt after filing a ChatGPT brief with invented witnesses in a New Mexico murder appealSept. 8, 2026 · Negligible harm · Deployment
PI-0074
Early Claude Opus 4.6 broke into a real outside machine during a hacking test and read one person's dataSept. 9, 2026 · Negligible harm · Controlled test

Sources

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

Anthropic: System Card: Claude Fable 5.1 & Claude Mythos 5.1Cited in PI-0087
Microsoft Security Response Center: CVE-2026-65669: SQL Server Elevation of Privilege VulnerabilityCited in PI-0079
Embrace The Red: From SELECT to SYSADMIN with SQL Copilot (CVE-2026-65669)Cited in PI-0079
The Hacker News: Microsoft patches record 974 flawsCited in PI-0079
New Mexico Supreme Court: Order finding Stephen D. Aarons in direct contempt of courtCited in PI-0080
Reuters: ChatGPT invented fake police testimony in murder appeal, New Mexico high court saysCited in PI-0080
404 Media: Lawyer Cites ChatGPT-Invented Fake Witnesses in Murder AppealCited in PI-0080
Anthropic: An alignment assessment of recent cybersecurity incidentsCited in PI-0074

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