Weekly reading · methodology v0.6
Window ending March 24, 2025
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 Feb. 23, 2025 through March 24, 2025. 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
2
Control failures only · No qualifying harm. The reading is the highest control level breached: 2, 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 counts in this week. The reading is the highest control level breached: 2 (set by 1 record: PI-0003). It is a level, not a count.
- Documented harm
- 0
- No harm found (stated scope)
- 0
- No harm reported
- 1
- Impact unknown
- 0
- Alleged, AI role uncorroborated
- 0
- Counts toward the index
- 0
- Unverified, watching
- 0
- Alleged in court
- 0
- Control failure, tracked
- 1
- Tracked separately
- 0
Documented exclusions: 0 internal; 0 awaiting evidence review. 0 qualifying records with a bounded single-source review.
Inspect the evidence · 1 record
- PI-0003 · OpenAI found a reasoning model reward hacking in training, then hiding its intent when penalizedNo harm reported · sets the reading: highest control level breached
Status totals cover counted records; aliases, superseded aggregates and records tracked separately are excluded.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-0003OpenAI found a reasoning model reward hacking in training, then hiding its intent when penalizedMarch 10, 2025 · No harm reported · Internal research
Sources
These links support the records above. Source availability and conclusions may change.
- OpenAI: Detecting misbehavior in frontier reasoning models (chain-of-thought monitoring)Cited in PI-0003
- arXiv: Monitoring Reasoning Models for Misbehavior and the Risks of Promoting ObfuscationCited in PI-0003
- Convergence India: Pressuring AI models to avoid cheating could backfire (page returned HTTP 500 when checked 3 Oct 2026)Cited in PI-0003
All weekly readings · How this reading is calculated · Download the weekly card
