AI Risk Wire

Corrections

A published case is never edited. Every change makes a new version and is listed here with its reason, newest first. JSON

744 changes to 213 cases; the latest was on 2026-10-25.

Reviewer corrections 357Rebuilt from sources 112Merges of duplicates 91Other changes 87Fields added by a model 40Retractions 34Confidence grades lowered 21Name spelling 2

Showing the 2 changes to this case. All changes

DateCaseWhat changedBy
2026-10-22Prompt-injected email assistant summary pushes employee toward fraudulent vendor payment
LR-2026-0135 · version 2 → 3
A judgement inferred by us that no source states was cleared.
What was changed: insurance, shared exposure, who was responsible, citations and 2 more
Srini Iyer
2026-10-11Prompt-injected email assistant summary pushes employee toward fraudulent vendor payment
LR-2026-0135 · version 1 → 2
Rebuilt from its cited sources on 2026-10-11.
What was changed: insurance, the evidence, industry, shared exposure and 21 more
Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-11
Automatic rebuild

Showing 1–2 of 2. Or take the JSON.