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 357 of 744: Reviewer corrections. All changes
| Date | Case | What changed | By |
|---|---|---|---|
| 2026-10-22 | AI agent (ARTEX with Claude) used in cyberattacks targeting South Korean banks LR-2026-0140 · version 6 → 7 | A denominator from another event or of another kind was cleared. What was changed: base count, notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | Autonomous AI agent framework (Strix/Cairn/Hermes) used to attack hundreds of online retailers and steal card data LR-2026-0133 · version 3 → 4 | Citations to sentences about a different event were removed; the sentence that states the denominator was cited. What was changed: citations, notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | South Korean government evaluation finds all tested autonomous AI agent models vulnerable to prompt injection and long-term memory attacks LR-2026-0130 · version 2 → 3 | Citations to sentences about a different event were removed; the sentence that states the denominator was cited. What was changed: citations, notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | Indirect prompt injection of AI email summarizer via forged header blocks in plain view LR-2026-0125 · version 2 → 3 | Citations to sentences about a different event were removed; the sentence that states the denominator was cited. What was changed: citations, notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | GitLab AI Gateway prompt template sandbox escape (CVE-2026-90970) LR-2026-0116 · version 4 → 5 | A value cited to a sentence about a different event or company was cleared; a value marked as inferred is stated by a cited sentence; regraded; citations to sentences about a different event were removed. What was changed: shared model, near miss, citations, notes on gaps and 2 more | Srini Iyer |
| 2026-10-22 | AI agents attempt unauthorized access to Library and Archives Canada website LR-2026-0111 · version 2 → 3 | A value marked as inferred is stated by a cited sentence; regraded; citations to sentences about a different event were removed. What was changed: notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | Meta Muse agent disclosed Marketplace seller's home address and impersonated him to a buyer LR-2026-0103 · version 3 → 4 | Citations to sentences about a different event were removed; the sentence that states the denominator was cited. What was changed: citations, notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | OpenAI agents bypass website security controls and republish SEC data LR-2026-0069 · version 7 → 8 | An event recorded in another case was counted here; severity now rests on this case's own event; citations to sentences about a different event were removed; linked to the records that report the same disclosure or name each… What was changed: related cases, summary, citations, notes on gaps and 3 more The whole reasonAn event recorded in another case was counted here; severity now rests on this case's own event; citations to sentences about a different event were removed; linked to the records that report the same disclosure or name each other. | Srini Iyer |
| 2026-10-22 | OpenAI agents leak 53 ChatGPT user images LR-2026-0068 · version 5 → 6 | Linked to the records that report the same disclosure or name each other. What was changed: related cases, notes on gaps | Srini Iyer |
| 2026-10-22 | Frontier LLM agent fabricated a complete calibration-comparison report for commands that never ran LR-2026-0051 · version 4 → 5 | A safeguard state its own quote contradicts was removed; 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: cause, cause in detail, summary, citations and 2 more | Srini Iyer |
| 2026-10-22 | OpenAI research models used internal Artifactory repository as a cross-sample message board during RL training LR-2026-0015 · version 10 → 11 | A value marked as inferred is stated by a cited sentence; regraded; citations to sentences about a different event were removed. What was changed: citations, notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | Unreleased OpenAI Astra-family model inserted jailbreak-like instructions into its own compaction summaries during RL training LR-2026-0011 · version 12 → 13 | A value marked as inferred is stated by a cited sentence; regraded; citations to sentences about a different event were removed. What was changed: citations, notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | OpenAI ExploitGym agents developed tool-call spoofing to falsify their own evaluation transcripts LR-2026-0004 · version 13 → 14 | Citations to sentences about a different event were removed. What was changed: citations, notes on gaps | Srini Iyer |
| 2026-10-22 | OpenAI agents built an unauthorized inter-agent message board inside the Artifactory package service LR-2026-0002 · version 12 → 13 | A value marked as inferred is stated by a cited sentence; regraded; citations to sentences about a different event were removed; web-page link text was cut from a quotation. What was changed: failed control, citations, notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | AISI cyber evaluation: Mythos 5 agent bypassed an audio CAPTCHA and abused a free DNS service to point a public record at an internal target LR-2026-0027 · version 11 → 12 | Citations to sentences about a different event were removed; the sentence that states the denominator was cited. What was changed: citations, notes on gaps, confidence grades | 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 8 → 9 | Citations to sentences about a different event were removed; the sentence that states the denominator was cited. What was changed: citations, notes on gaps, confidence grades | 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 13 → 14 | Citations to sentences about a different event were removed; the sentence that states the denominator was cited. What was changed: citations, notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | AISI cyber evaluation: Mythos 5 agent mass-created malicious GitHub repositories and its packages executed in Dependabot containers LR-2026-0024 · version 8 → 9 | Citations to sentences about a different event were removed; the sentence that states the denominator was cited. What was changed: citations, notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | AISI cyber evaluation: Mythos 5 agent sent deceptive targeted emails and file transfers to real open-source maintainers LR-2026-0023 · version 10 → 11 | Citations to sentences about a different event were removed; the sentence that states the denominator was cited. What was changed: citations, notes on gaps, confidence grades | 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 10 → 11 | Citations to sentences about a different event were removed; the sentence that states the denominator was cited. What was changed: citations, notes on gaps, confidence grades | 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 11 → 12 | A value marked as inferred is stated by a cited sentence; regraded; citations to sentences about a different event were removed; the sentence that states the denominator was cited. What was changed: citations, notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | Unreleased OpenAI model used a leaked GitHub API key, attempted disposable-email signups, then fabricated earnings data during RL training LR-2026-0013 · version 15 → 16 | A denominator from another event or of another kind was cleared; a value marked as inferred is stated by a cited sentence; regraded; citations to sentences about a different event were removed. What was changed: base count, citations, notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | Agentic NanoGPT optimization runs attempt reward hacking with brittle curve-fit optimizations LR-2026-0092 · version 6 → 7 | Citations to sentences about a different event were removed; the sentence that states the denominator was cited. What was changed: citations, notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | OpenAI evaluation agents compromised Hugging Face production infrastructure while seeking ExploitGym solutions LR-2026-0003 · version 14 → 15 | A value marked as inferred is stated by a cited sentence; regraded; citations to sentences about a different event were removed; web-page link text was cut from a quotation. What was changed: failed control, citations, notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | Replit AI agent deleted SaaStr's production database during a declared code freeze and stated rollback was impossible LR-2025-0031 · version 10 → 11 | A value marked as inferred is stated by a cited sentence; regraded; citations to sentences about a different event were removed. What was changed: notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | Character.AI chatbot alleged to have encouraged 14-year-old's suicide (Garcia v. Character.AI) LR-2026-0100 · version 6 → 7 | Linked to the records that report the same disclosure or name each other. What was changed: related cases, notes on gaps | Srini Iyer |
| 2026-10-22 | Anthropic Claude models gained unauthorized access to real third-party systems during evaluations LR-2026-0237 · 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; linked to the records that report the same disclosure or name each other. What was changed: related cases, where its input came from, themes, citations and 7 more | Srini Iyer |
| 2026-10-22 | Personal AI agent hacks gym waitlist and deletes two users, cannot reverse action LR-2026-0190 · 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 | Astra agent fails to find Lean4 set-theory embedding after ~25h and several thousand dollars LR-2026-0149 · version 5 → 6 | 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: who was responsible, cause, cause in detail, summary and 3 more | Srini Iyer |
| 2026-10-22 | Deepfake investment-scam ads impersonating Nigerian public figures on Facebook LR-2026-0139 · 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. What was changed: citations, notes on gaps, confidence grades, safeguards in place | Srini Iyer |
| 2026-10-22 | AISI cyber evaluation: Mythos 5 agent bypassed an audio CAPTCHA and abused a free DNS service to point a public record at an internal target LR-2026-0027 · version 10 → 11 | A value cited to a sentence about a different event or company was cleared; citations to sentences about a different event were removed. What was changed: citations, notes on gaps, confidence grades, what it was for | 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 7 → 8 | Citations to sentences about a different event were removed. What was changed: citations, 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 12 → 13 | A value cited to a sentence about a different event or company was cleared; citations to sentences about a different event were removed. What was changed: who was responsible, citations, notes on gaps, confidence grades and 1 more | Srini Iyer |
| 2026-10-22 | AISI cyber evaluation: Mythos 5 agent mass-created malicious GitHub repositories and its packages executed in Dependabot containers LR-2026-0024 · version 7 → 8 | A value cited to a sentence about a different event or company was cleared; citations to sentences about a different event were removed; linked to the records that report the same disclosure or name each other; severity reason… What was changed: related cases, failure class, where its input came from, near miss and 6 more The whole reasonA value cited to a sentence about a different event or company was cleared; citations to sentences about a different event were removed; linked to the records that report the same disclosure or name each other; severity reason did not fit its quote or the record; summary or story described a different event or the article, not this event. | Srini Iyer |
| 2026-10-22 | AISI cyber evaluation: Mythos 5 agent sent deceptive targeted emails and file transfers to real open-source maintainers LR-2026-0023 · version 9 → 10 | A value cited to a sentence about a different event or company was cleared; citations to sentences about a different event were removed. What was changed: themes, citations, notes on gaps, confidence grades and 1 more | 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 9 → 10 | Citations to sentences about a different event were removed; linked to the records that report the same disclosure or name each other; summary or story described a different event or the article, not this event. What was changed: related cases, summary, citations, notes on gaps and 1 more | Srini Iyer |
| 2026-10-22 | Storm-0940 uses ARTEX agentic AI framework to automate cross-tenant password spraying and OAuth application abuse LR-2026-0235 · 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; 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 | AI-generated 'Xiaohai' teen persona used to sell products to older women via fabricated sob stories LR-2026-0227 · version 2 → 3 | Severity reason did not fit its quote or the record. What was changed: notes on gaps, why this severity | Srini Iyer |
| 2026-10-22 | Grok chatbot on X repeated alleged name of Cornell 'Jane Doe' in replies, amplifying doxing LR-2026-0218 · version 3 → 4 | Citations to sentences about a different event were removed; developer named by a cited sentence about this event. What was changed: citations, notes on gaps, developer | Srini Iyer |
| 2026-10-22 | OpenAI research model accessed a cryptocurrency wallet without permission LR-2026-0214 · version 2 → 3 | Severity reason did not fit its quote or the record. What was changed: notes on gaps, why this severity | Srini Iyer |
Showing 161–200 of 357 · page 5 of 9. ‹ Previous · Next › Or take the JSON.