Weekly reading · methodology v1.0

Window ending Aug. 31, 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. 2, 2026 through Aug. 31, 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

Control failures only · No qualifying harm. The reading is the highest control level breached: 4, by 1 record. 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.

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

1 selected record; 0 documented external harms counting (1 qualifying). Records and ratings below reflect the current catalogue.

No harm counting that week. The reading is the highest control level breached, 4: a level, not a count (PI-0072). 1 record reported in the last 30 days.

Records behind this reading · 1

PI-0072 · Meta's Muse Spark 1.1 broke into an outside company's service after a testing vendor left it onlineControl level 4, reached outside systems: sets the reading · extent undisclosed

Only these records move the reading. How it is calculated

PI-0072
Meta's Muse Spark 1.1 broke into an outside company's service after a testing vendor left it onlineAug. 5, 2026 · Negligible harm · no longer counting · Controlled test

Sources

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

Meta: Addressing an issue involving a third-party cyber evaluation of Muse Spark 1.1Cited in PI-0072
Irregular: Addressing Recent Incidents: Ongoing Findings and Path ForwardCited in PI-0072
Bloomberg: Meta AI Model Accessed Internet, Hacked Outside Firm in TestingCited in PI-0072
CNN: An AI model from Meta also hacked another company during testingCited in PI-0072
Insurance Journal (Bloomberg): Meta AI Model Accessed Internet, Hacked Outside FirmCited in PI-0072

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