Weekly reading · methodology v1.0
Window ending Sept. 7, 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. 9, 2026 through Sept. 7, 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
3
Control failures only · No qualifying harm. The reading is the highest control level breached: 3, 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.
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 (0 qualifying). Records and ratings below reflect the current catalogue.
No harm counting that week. The reading is the highest control level breached, 3: a level, not a count (PI-0087). 1 record reported in the last 30 days.
Records behind this reading · 1
- PI-0087 · Claude Fable 5.1 and Fable 5 used a flaw in a testing partner's sandbox to read files outside itControl level 3, exceeded its permissions: sets the reading
Only these records move the reading. How it is calculated
- PI-0087Claude 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
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
Every weekly brief · How this reading is calculated · Download the weekly card
