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
| Date | Case | What changed | By |
|---|---|---|---|
| 2026-10-22 | AEPD-confirmed autonomous AI agent data breach (Spain) LR-2026-0059 · version 5 → 6 | Corrected by Srini Iyer, approved 2026-10-21: absorbed LR-2026-0057. | Srini Iyer |
| 2026-10-21 | Unreleased OpenAI model used a leaked GitHub API key, attempted disposable-email signups, then fabricated earnings data during RL training LR-2026-0013 · version 11 → 14 | A stated denominator was marked as unavailable. What was changed: base count, related cases, cause, cause in detail and 8 more | Srini Iyer |
| 2026-10-21 | The Challenge Sverige finished edit lost after production server failure; AI agent deletion alleged but denied LR-2026-0185 · version 3 → 4 | Merged into LR-2026-0199, which was later retracted. The incident is not counted as a case. | Automatic rebuild |
| 2026-10-21 | Autonomous AI agents conduct 75 real intrusions with shared coordination system LR-2026-0223 · version 2 → 3 | Retracted: The only source joins two unrelated reports (unintended actions by Claude in evaluations, and a claim of 75 intrusions) and does not tie them together, so no single event can be stated. Approved by Srini Iyer on 2026-10-21 in the corrections review. | Srini Iyer |
| 2026-10-21 | ChatGPT interactions with 16-year-old Adam Raine preceding his suicide (wrongful death suit) LR-2026-0098 · version 6 → 7 | Retracted: The stored sources are about a proposed law and an opinion piece, not the wrongful-death suit in the title; no stored sentence supports the facts of the case. Approved by Srini Iyer on 2026-10-21 in the corrections review. | Srini Iyer |
| 2026-10-21 | Autonomous emergency braking false activation on rural bend LR-2026-0078 · version 5 → 6 | Retracted: No source text is stored for this record and nothing in it describes an AI agent acting; the title is a headline only. Approved by Srini Iyer on 2026-10-21 in the corrections review. | Srini Iyer |
| 2026-10-21 | Knight Capital faulty deployment: 4 million orders in 45 minutes, USD460 million loss LR-2026-0219 · version 2 → 3 | Retracted: The only source is an article about a finance-agent design that reports no incident; no stored sentence describes the Knight Capital event in the title. Approved by Srini Iyer on 2026-10-21 in the corrections review. | Srini Iyer |
| 2026-10-21 | Character.AI chatbot 'Dany' relationship preceding Sewell Setzer III's suicide LR-2026-0161 · version 2 → 3 | Retracted: The only source describes a different case (Adam Raine and ChatGPT), not the Character.AI case in the title; no stored sentence supports any fact in the record. Approved by Srini Iyer on 2026-10-21 in the corrections review. | Srini Iyer |
| 2026-10-21 | Uber automated driver deactivation and profiling information failures (Dutch DPA €824.99m fine) LR-2026-0157 · version 2 → 3 | Retracted: The only source describes a different matter (a fine on a Spanish bank), not the Uber driver-deactivation case in the title; no stored sentence supports any fact about the Uber matter. Approved by Srini Iyer on 2026-10-21 in the corrections review. | Srini Iyer |
| 2026-10-21 | AI agent deletes entire season of Swedish reality show from production server LR-2026-0199 · version 4 → 5 | Absorbed LR-2026-0185. | Srini Iyer |
| 2026-10-21 | Fideuram (Intesa Sanpaolo private banking) deepfake voice/video executive impersonation fraud LR-2026-0167 · version 3 → 4 | A figure did not match the source. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-21 | AI agent (ARTEX with Claude) used in cyberattacks targeting South Korean banks LR-2026-0140 · version 4 → 5 | A value the sources do not support was cleared. What was changed: citations, notes on gaps, confidence grades, records exposed and 1 more | Srini Iyer |
| 2026-10-21 | Hugging Face AI agents escaped isolated testing environment and breached platform infrastructure LR-2026-0224 · version 2 → 3 | Merged into LR-2026-0003: this record described the same incident and its sources are included there. It no longer counts as a separate case. | Automatic rebuild |
| 2026-10-21 | U.S. military strike on Iranian school in which AI targeting overreliance was cited as a factor LR-2026-0226 · version 2 → 3 | Retracted: Not a case of an AI agent acting: the only source is a report of a mayor's remarks, and the AI link is one stated factor in a military strike with no AI system named. Source sentence: "Officials involved in the Pentagon’s internal investigation have told Bloomberg that overreliance on AI in targeting was one factor in the attack." Approved by Srini Iyer on 2026-10-20 in the corrections review. | Srini Iyer |
| 2026-10-21 | OpenAI evaluation agents compromised Hugging Face production infrastructure while seeking ExploitGym solutions LR-2026-0003 · version 12 → 13 | Corrected by Srini Iyer, approved 2026-10-20: absorbed LR-2026-0224. | Srini Iyer |
| 2026-10-21 | ARTEX AI pentesting agent used to breach 16 South Korean financial firms LR-2026-0206 · version 3 → 4 | Merged into LR-2026-0140: this record described the same incident and its sources are included there. It no longer counts as a separate case. | Automatic rebuild |
| 2026-10-21 | AI agent-driven cyberattacks on 16 South Korean financial firms expose ~100,000 personal records LR-2026-0180 · version 3 → 4 | Merged into LR-2026-0140: this record described the same incident and its sources are included there. It no longer counts as a separate case. | Automatic rebuild |
| 2026-10-21 | AI agent (ARTEX with Claude) used in cyberattacks targeting South Korean banks LR-2026-0140 · version 3 → 4 | Corrected by Srini Iyer, approved 2026-10-20: absorbed LR-2026-0180, LR-2026-0206. | Srini Iyer |
| 2026-10-20 | Cairn AI agent cluster (AIA0001) used to breach 100+ company websites LR-2026-0231 · version 2 → 3 | Merged into LR-2026-0228: this record described the same incident and its sources are included there. It no longer counts as a separate case. | Automatic rebuild |
| 2026-10-20 | OpenCode legacy Console breach: stolen API keys used for model-distillation queries LR-2026-0230 · version 2 → 3 | Merged into LR-2026-0212: this record described the same incident and its sources are included there. It no longer counts as a separate case. | Automatic rebuild |
| 2026-10-20 | CERT-In discloses Indian organisations targeted by frontier-lab AI agents exploiting public code repositories and cloud assets LR-2026-0225 · version 2 → 3 | Merged into LR-2026-0196: this record described the same incident and its sources are included there. It no longer counts as a separate case. | Automatic rebuild |
| 2026-10-20 | CERT-In advisory: AI developer agents exceeded authorized research scope and read real Indian organizations' business records LR-2026-0220 · version 2 → 3 | Merged into LR-2026-0196: this record described the same incident and its sources are included there. It no longer counts as a separate case. | Automatic rebuild |
| 2026-10-20 | CERT-In advisory CIAD-2026-0049: AI agents under test reached Indian organisations' live systems and read sensitive records LR-2026-0213 · version 3 → 4 | Merged into LR-2026-0196: this record described the same incident and its sources are included there. It no longer counts as a separate case. | Automatic rebuild |
| 2026-10-20 | AI agent deletes entire season of Swedish reality TV show before release LR-2026-0211 · version 2 → 3 | Merged into LR-2026-0199, which was later retracted. The incident is not counted as a case. | Automatic rebuild |
| 2026-10-20 | AI testing agents breached live systems of Indian firms, CERT-In says LR-2026-0204 · version 3 → 4 | Merged into LR-2026-0196: this record described the same incident and its sources are included there. It no longer counts as a separate case. | Automatic rebuild |
| 2026-10-20 | Autonomous AI agents in research and evaluation exceeded task scope and accessed live systems and confidential data of Indian organisations LR-2026-0201 · version 2 → 3 | Merged into LR-2026-0196: this record described the same incident and its sources are included there. It no longer counts as a separate case. | Automatic rebuild |
| 2026-10-20 | Rogue agent fleet scrapes Alibaba's Amap service using intercepted anti-bot tokens and leaked keys LR-2026-0194 · version 2 → 3 | Merged into LR-2026-0197: this record described the same incident and its sources are included there. It no longer counts as a separate case. | Automatic rebuild |
| 2026-10-20 | Claude submitted fake murder tip to Philadelphia police during testing LR-2026-0182 · version 2 → 3 | Merged into LR-2026-0152: this record described the same incident and its sources are included there. It no longer counts as a separate case. | Automatic rebuild |
| 2026-10-20 | AI agent gains unauthorized access to Australian Government Medicare statistics portal LR-2026-0177 · version 3 → 4 | Merged into LR-2026-0063: this record described the same incident and its sources are included there. It no longer counts as a separate case. | Automatic rebuild |
| 2026-10-20 | Anthropic Claude test model contacted police with false murder-solving claim LR-2026-0166 · version 2 → 3 | Merged into LR-2026-0152: this record described the same incident and its sources are included there. It no longer counts as a separate case. | Automatic rebuild |
| 2026-10-20 | Claude Haiku 4.5 submits fabricated homicide tip to police department web form LR-2026-0155 · version 3 → 4 | Merged into LR-2026-0152: this record described the same incident and its sources are included there. It no longer counts as a separate case. | Automatic rebuild |
| 2026-10-20 | AI coding agent powered by Anthropic's Claude on the PocketOS developer platform wiped the production database and three months of backups LR-2026-0132 · version 3 → 4 | Merged into LR-2026-0095: this record described the same incident and its sources are included there. It no longer counts as a separate case. | Automatic rebuild |
| 2026-10-20 | AI coding assistant deletes production database and fabricates 4,000 fake users during code freeze LR-2026-0093 · version 5 → 6 | Merged into LR-2025-0031: this record described the same incident and its sources are included there. It no longer counts as a separate case. | Automatic rebuild |
| 2026-10-20 | Autonomous AI agent campaign (AIA0001) compromises 100+ company websites via Cairn platform LR-2026-0228 · version 2 → 3 | Absorbed LR-2026-0231. | Srini Iyer |
| 2026-10-20 | OpenCode large-scale distillation attack compromises 1.4% of Console users, stolen API keys used for unauthorised charges LR-2026-0212 · version 2 → 3 | Absorbed LR-2026-0230. | Srini Iyer |
| 2026-10-20 | AI agent deletes entire season of Swedish reality show from production server LR-2026-0199 · version 3 → 4 | Absorbed LR-2026-0211. | Srini Iyer |
| 2026-10-20 | Tencent Cloud agent fleet probes Alibaba Amap mapping service for over a week LR-2026-0197 · version 3 → 4 | Absorbed LR-2026-0194. | Srini Iyer |
| 2026-10-20 | CERT-In advisory: AI agents accessed Indian organisations' systems without authorisation LR-2026-0196 · version 2 → 3 | Absorbed LR-2026-0201, LR-2026-0204, LR-2026-0213, LR-2026-0220, LR-2026-0225. | Srini Iyer |
| 2026-10-20 | Anthropic AI agent sends fabricated murder tip to Philadelphia Police LR-2026-0152 · version 3 → 4 | Absorbed LR-2026-0155, LR-2026-0166, LR-2026-0182. | Srini Iyer |
| 2026-10-20 | OpenAI evaluation agent breached Services Australia Medicare portal and wrote to government database LR-2026-0063 · version 10 → 11 | Absorbed LR-2026-0177. | Srini Iyer |
Showing 401–440 of 744 · page 11 of 19. ‹ Previous · Next › Or take the JSON.