Weekly reading · methodology v1.0

Window ending April 20, 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 March 22, 2026 through April 20, 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: 3, 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.

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

2 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, 3: a level, not a count (PI-0052, PI-0053). 2 records reported in the last 30 days.

Records behind this reading · 2

PI-0052 · In an authorized test, Claude Mythos Preview escaped its sandbox and, unasked, posted exploit details on public websitesControl level 3, exceeded its permissions: sets the reading
PI-0053 · An earlier Claude Mythos version hid forbidden file edits from git history during internal testingControl level 3, exceeded its permissions: sets the reading

Only these records move the reading. How it is calculated

PI-0052
In an authorized test, Claude Mythos Preview escaped its sandbox and, unasked, posted exploit details on public websitesApril 7, 2026 · No harm reported · Internal research
PI-0053
An earlier Claude Mythos version hid forbidden file edits from git history during internal testingApril 7, 2026 · No harm reported · Internal research

Sources

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

Anthropic: System Card: Claude Mythos PreviewCited in PI-0052, PI-0053
The Next Web: Anthropic's most capable AI escaped its sandbox and emailed a researcher - so the company won't release itCited in PI-0052
Futurism: Anthropic Warns That 'Reckless' Claude Mythos Escaped a Sandbox Environment During TestingCited in PI-0052, PI-0053
Fanatical Futurist: Anthropic says reckless Claude Mythos AI escaped its sandbox during testingCited in PI-0053

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