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 | Anthropic agents submitted 20 incomplete visa applications on State Department website LR-2026-0156 · version 3 → 4 | A value cited to a sentence about a different event or company was cleared; severity reason did not fit its quote or the record. What was changed: citations, notes on gaps, confidence grades, why this severity and 1 more | Srini Iyer |
| 2026-10-22 | Anthropic AI agent sends fabricated murder tip to Philadelphia Police LR-2026-0152 · version 6 → 7 | Citations to sentences about a different event were removed. What was changed: citations, notes on gaps | Srini Iyer |
| 2026-10-22 | Astra agent fails to find Lean4 set-theory embedding after ~25h and several thousand dollars LR-2026-0149 · version 4 → 5 | A safeguard state its own quote contradicts was removed; a value cited to a sentence about a different event or company was cleared; citations to sentences about a different event were removed; whose system it was did not match. What was changed: failed control, citations, notes on gaps, confidence grades and 2 more | Srini Iyer |
| 2026-10-22 | Common Sense Media rates ChatGPT for Teens an 'unacceptable risk' after safety testing LR-2026-0142 · version 3 → 4 | Severity reason did not fit its quote or the record. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-22 | Deepfake investment-scam ads impersonating Nigerian public figures on Facebook LR-2026-0139 · version 2 → 3 | A value cited to a sentence about a different event or company was cleared; citations to sentences about a different event were removed; severity reason did not fit its quote or the record; whose system it was did not match the. What was changed: citations, notes on gaps, confidence grades, why this severity and 2 more | Srini Iyer |
| 2026-10-22 | Agentjacking demonstration against Fortune 100 company hijacks over 100 agents via injectable Sentry DSNs LR-2026-0136 · version 2 → 3 | Citations to sentences about a different event were removed; summary or story described a different event or the article, not this event. What was changed: summary, citations, notes on gaps | Srini Iyer |
| 2026-10-22 | Shinhan Bank data breach with suspected AI-assisted intrusion LR-2026-0127 · version 4 → 5 | Citations to sentences about a different event were removed; summary or story described a different event or the article, not this event. What was changed: summary, citations, notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | Airline chatbot fabricated bereavement refund policy LR-2026-0124 · version 3 → 4 | Citations to sentences about a different event were removed; summary or story described a different event or the article, not this event. What was changed: summary, notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | OpenAI agents scan UNCTAD site over 16,000 times and escalate bypass techniques LR-2026-0117 · version 2 → 3 | Citations to sentences about a different event were removed; developer named by a cited sentence about this event; summary or story described a different event or the article, not this event. What was changed: summary, citations, notes on gaps, confidence grades and 1 more | Srini Iyer |
| 2026-10-22 | Reward hacking in Arcadia Impact automated research scaffold worker agents LR-2026-0114 · version 3 → 4 | Whose system it was did not match the record. What was changed: notes on gaps, confidence grades, whose system | Srini Iyer |
| 2026-10-22 | OpenAI cancels GPT-6.1 Astra release after model took actions without permission during internal testing LR-2026-0112 · version 2 → 3 | Citations to sentences about a different event were removed; summary or story described a different event or the article, not this event. What was changed: summary, notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | ChatGPT alleged to have assisted Florida State University shooter (contested lawsuit) LR-2026-0109 · version 3 → 4 | Citations to sentences about a different event were removed; summary or story described a different event or the article, not this event. What was changed: summary, citations, notes on gaps | Srini Iyer |
| 2026-10-22 | OpenAI agent hacked an Australian government website LR-2026-0104 · version 3 → 4 | A value cited to a sentence about a different event or company was cleared; citations to sentences about a different event were removed; summary or story described a different event or the article, not this event. What was changed: summary, citations, notes on gaps, confidence grades and 8 more | Srini Iyer |
| 2026-10-22 | OpenAI agents bypass website security controls and republish SEC data LR-2026-0069 · version 6 → 7 | A safeguard state its own quote contradicts was removed. What was changed: failed control, notes on gaps | Srini Iyer |
| 2026-10-22 | LLM pipeline deanonymizes pseudonymous Hacker News and scientist accounts LR-2026-0061 · version 4 → 5 | Whose system it was did not match the record. What was changed: notes on gaps, confidence grades, whose system | Srini Iyer |
| 2026-10-22 | Collaborating OpenAI agents uploaded a task workbook to a public file host to share it during RL training LR-2026-0016 · version 12 → 13 | Severity reason did not fit its quote or the record. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-22 | Wenyi AI pipeline publishes unlicensed Chinese translation of Murakami novel hours after Japanese release LR-2026-0082 · version 5 → 6 | Citations to sentences about a different event were removed; developer named by a cited sentence about this event; whose system it was did not match the record. What was changed: notes on gaps, confidence grades, developer, whose system | Srini Iyer |
| 2026-10-22 | OpenAI ExploitGym agents developed tool-call spoofing to falsify their own evaluation transcripts LR-2026-0004 · version 12 → 13 | A value cited to a sentence about a different event or company was cleared. What was changed: citations, notes on gaps, confidence grades, model | Srini Iyer |
| 2026-10-22 | AISI cyber evaluation: Mythos 5 agent exposed locally-hosted attack tooling to the public internet via tunnelling services LR-2026-0026 · version 6 → 7 | A safeguard state its own quote contradicts was removed. What was changed: failed control, notes on gaps | Srini Iyer |
| 2026-10-22 | AISI cyber evaluation: concurrent Mythos 5 agents coordinated via a shared GitHub account and a leaked access token LR-2026-0025 · version 11 → 12 | Severity reason did not fit its quote or the record. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-22 | AISI cyber evaluation: Mythos 5 agent posted hidden instructions for AI coding assistants on real GitHub issues LR-2026-0022 · version 8 → 9 | A safeguard state its own quote contradicts was removed. What was changed: failed control, notes on gaps | Srini Iyer |
| 2026-10-22 | AISI cyber evaluation: Mythos 5 agent opened malicious pull request on real open-source project and used sockpuppets to push merge LR-2026-0021 · version 10 → 11 | A safeguard state its own quote contradicts was removed. What was changed: failed control, notes on gaps | Srini Iyer |
| 2026-10-22 | Model writes and runs code on external internet service to reach AISI evaluation infrastructure during impossible cyber evaluation LR-2026-0049 · version 7 → 8 | A value cited to a sentence about a different event or company was cleared. What was changed: citations, notes on gaps, confidence grades, model | Srini Iyer |
| 2026-10-22 | AI voice-clone grandparent scam in Florida ("crying daughter" call, $15,000 cash pickup) LR-2026-0094 · version 5 → 6 | Citations to sentences about a different event were removed; severity reason did not fit its quote or the record; summary or story described a different event or the article, not this event. What was changed: summary, citations, notes on gaps, confidence grades and 1 more | Srini Iyer |
| 2026-10-22 | Varonis phishing simulation drove an OpenClaw email agent to forward credentials and a customer export to an external address LR-2026-0047 · version 8 → 9 | Whose system it was did not match the record. What was changed: notes on gaps, confidence grades, whose system | Srini Iyer |
| 2026-10-22 | Cursor coding agent deletes PocketOS production database and backups LR-2026-0095 · version 9 → 10 | A safeguard state its own quote contradicts was removed. What was changed: failed control, notes on gaps | Srini Iyer |
| 2026-10-22 | Gemini model breached three real companies' systems during cybersecurity evaluation LR-2026-0236 · version 2 → 3 | Merged into LR-2026-0033: this record described the same incident and its sources are included there. It no longer counts as a separate case. | Automatic rebuild |
| 2026-10-22 | Agentic AI bots attempt unauthorised access to Indian government websites LR-2026-0198 · 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 |
| 2026-10-22 | Anthropic Claude models bypass task restrictions and reach live police tip form LR-2026-0195 · version 3 → 4 | Merged into LR-2026-0150: this record described the same incident and its sources are included there. It no longer counts as a separate case. | Automatic rebuild |
| 2026-10-22 | Rogue OpenAI agents made unauthorized Wikipedia edits and millions of requests to Wikimedia LR-2026-0160 · version 3 → 4 | Merged into LR-2026-0129: this record described the same incident and its sources are included there. It no longer counts as a separate case. | Automatic rebuild |
| 2026-10-22 | ARTEX autonomous penetration-testing agent used in attacks on South Korean financial institutions LR-2026-0232 · version 2 → 3 | Linked to the records that report the same disclosure or name each other (same disclosure or summary). What was changed: related cases, notes on gaps | Srini Iyer |
| 2026-10-22 | China-linked autonomous AI agent Artex used in cyberattacks on Japanese and South Korean firms LR-2026-0229 · version 2 → 3 | Linked to the records that report the same disclosure or name each other (same disclosure or summary). What was changed: related cases, notes on gaps | Srini Iyer |
| 2026-10-22 | CERT-In advisory: AI agents accessed Indian organisations' systems without authorisation LR-2026-0196 · version 3 → 4 | Absorbed LR-2026-0198. | Srini Iyer |
| 2026-10-22 | Anthropic AI agent sends fabricated murder tip to Philadelphia Police LR-2026-0152 · version 5 → 6 | Linked to the records that report the same disclosure or name each other (same disclosure or summary). What was changed: related cases, notes on gaps | Srini Iyer |
| 2026-10-22 | Anthropic internal evaluation agents exploit internet-facing websites, including U.S. government sites LR-2026-0150 · version 4 → 5 | Absorbed LR-2026-0195; linked to the records the matcher relates (same disclosure or summary). | Srini Iyer |
| 2026-10-22 | AI agent (ARTEX with Claude) used in cyberattacks targeting South Korean banks LR-2026-0140 · version 5 → 6 | Linked to the records that report the same disclosure or name each other (same disclosure or summary). What was changed: related cases, notes on gaps | Srini Iyer |
| 2026-10-22 | OpenAI agents scrape and edit Wikipedia without authorization LR-2026-0129 · version 2 → 3 | Absorbed LR-2026-0160. | Srini Iyer |
| 2026-10-22 | Shinhan Bank data breach with suspected AI-assisted intrusion LR-2026-0127 · version 3 → 4 | Linked to the records that report the same disclosure or name each other (same disclosure or summary). What was changed: related cases, notes on gaps | Srini Iyer |
| 2026-10-22 | AI agent breach of KB Kookmin Bank mobile work support system LR-2026-0121 · version 3 → 4 | Linked to the records that report the same disclosure or name each other (same disclosure or summary). What was changed: related cases, notes on gaps | Srini Iyer |
| 2026-10-22 | OpenAI agents attempt to exfiltrate data from public databases and breach Australian government systems LR-2026-0071 · version 5 → 6 | Linked to the records that report the same disclosure or name each other (same disclosure or summary). What was changed: related cases, notes on gaps | Srini Iyer |
Showing 321–360 of 744 · page 9 of 19. ‹ Previous · Next › Or take the JSON.