Weekly reading · methodology v0.6
Window ending April 13, 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 15, 2026 through April 13, 2026. A selected catalogue of reported AI incidents, reviewed through Oct. 7, 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
6
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.
This is a backcast from the current catalogue. It was not a reading published at the time.
Records behind this reading
3 selected records; 1 documented external harm counting (1 qualifying). Records and ratings below reflect the current catalogue.
1 qualifying harm record. Extent undisclosed for this record.
- Documented harm
- 1
- No harm found (stated scope)
- 0
- No harm reported
- 2
- Impact unknown
- 0
- Alleged, AI role uncorroborated
- 0
- Counts toward the index
- 1
- Unverified, watching
- 0
- Alleged in court
- 0
- Control failure, tracked
- 2
- Tracked separately
- 0
Documented exclusions: 0 internal; 0 awaiting evidence review. 0 qualifying records with a bounded single-source review.
Inspect the evidence · 3 records
- PI-0051 · Internal agent posted unrequested advice that led to a two-hour internal data exposureDocumented harm · qualifying harm, counting as negligible, rated minor · extent undisclosed
- PI-0052 · In an authorized test, Claude Mythos Preview escaped its sandbox and, unasked, posted exploit details on public websitesNo harm reported · excluded from the harm reading
- PI-0053 · An earlier Claude Mythos version hid forbidden file edits from git history during internal testingNo harm reported · excluded from the harm reading
Status totals cover counted records; aliases, superseded aggregates and records tracked separately are excluded. Eligibility and extent notes overlap those totals. These observations are not statistical uncertainty bounds.
- PI-0051Internal agent posted unrequested advice that led to a two-hour internal data exposureMarch 18, 2026 · Minor harm · counting as negligible, rated minor · Deployment
- PI-0052In 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-0053An 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.
- The Information: Inside Meta, a Rogue AI Agent Triggers Security AlertCited in PI-0051
- The Decoder: A rogue AI agent caused a serious security incident at MetaCited in PI-0051
- TechCrunch: Meta is having trouble with rogue AI agentsCited in PI-0051
- The Verge: A rogue AI led to a serious security incident at MetaCited in PI-0051
- Sumsub: Rogue AI agent at Meta triggers security incidentCited in PI-0051
- Unite.AI: Meta AI agent triggers Sev 1 security incident after acting without authorizationCited in PI-0051
- AI Incident Database: AI Incident Database report 7169Cited in PI-0051
- 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
All weekly readings · How this reading is calculated · Download the weekly card
