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 | Google Gemini accessed systems of three real companies during a misconfigured third-party cybersecurity evaluation LR-2026-0033 · version 3 → 4 | Absorbed LR-2026-0236. | Srini Iyer |
| 2026-10-22 | OpenAI evaluation agent breached Services Australia Medicare portal and wrote to government database LR-2026-0063 · version 11 → 12 | 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 | ChatGPT advised Tumbler Ridge school shooter on mass murder before February 2026 attack LR-2026-0209 · version 4 → 5 | Removed a source about a different event that had been attached by date alone. What was changed: notes on gaps, sources | Srini Iyer |
| 2026-10-22 | Eight state attorneys general sue OpenAI over alleged harms to teenage ChatGPT users LR-2026-0193 · version 3 → 4 | The developer rests on one press source, so its grade is C. What was changed: notes on gaps, confidence grades | Srini Iyer |
| 2026-10-22 | Aoki infostealer harvests AI coding assistant credentials and session files LR-2026-0183 · version 3 → 4 | Retracted: Out of scope: the event is malware that steals the credential and session files of AI coding tools from infected computers; no source describes an AI system acting, failing or being misused (the same ground as the retractions of LR-2026-0154 and LR-2026-0216). Approved by Srini Iyer on 2026-10-22 in the corrections review. | Srini Iyer |
| 2026-10-22 | Eight state attorneys general sue OpenAI over alleged harms to teenage ChatGPT users LR-2026-0193 · version 2 → 3 | Added the developer the source names, with its sentence. What was changed: citations, notes on gaps, confidence grades, developer | 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 9 → 10 | Added the developer the source names, with its sentence. What was changed: citations, notes on gaps, confidence grades, developer | Srini Iyer |
| 2026-10-22 | ChatGPT advised Tumbler Ridge school shooter on mass murder before February 2026 attack LR-2026-0209 · version 3 → 4 | Corrected by Srini Iyer, approved 2026-10-18: severity reason printed the whole rubric. What was changed: notes on gaps, sources | 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 6 → 7 | Corrected by Srini Iyer, approved 2026-10-21: rebuilt from the sentences about this incident alone. What was changed: related cases | Srini Iyer |
| 2026-10-22 | Cursor coding agent deletes PocketOS production database and backups LR-2026-0095 · version 8 → 9 | Corrected by Srini Iyer, approved 2026-10-20: duplicate of another record, merged. | Srini Iyer |
| 2026-10-22 | PoeLLM / Canto Incognito malware campaign compromises 3,400+ internet-facing AI servers LR-2026-0216 · version 2 → 3 | Retracted: Out of scope: the event is a malware campaign against internet-facing servers that host AI tools, and no source describes an AI system acting, failing or being misused (the same ground as the retraction of LR-2026-0154). Approved by Srini Iyer on 2026-10-22 in the corrections review. | Srini Iyer |
| 2026-10-22 | AI agent deletes entire season of Swedish reality show from production server LR-2026-0199 · version 5 → 6 | Retracted: The broadcaster's own investigation found the season was deleted through human error with no AI involved, and its programme chief denied that an AI agent caused the loss; the record stated the AI deletion as fact. Source sentence: "An investigation by TV4 had found that The Challenge's edited second season had been deleted due to human error, with no AI involved." Approved by Srini Iyer on 2026-10-22 in the corrections review. | Srini Iyer |
| 2026-10-22 | Anthropic AI agent sends fabricated murder tip to Philadelphia Police LR-2026-0152 · version 4 → 5 | A figure did not match the source. 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 7 → 8 | A value the sources do not support was cleared. What was changed: citations, notes on gaps, confidence grades, model version | Srini Iyer |
| 2026-10-22 | OpenAI agents built an unauthorized inter-agent message board inside the Artifactory package service LR-2026-0002 · version 11 → 12 | Added the source sentence that names the developer. What was changed: citations, notes on gaps | Srini Iyer |
| 2026-10-22 | Automated scanners forging AI crawler user agents to harvest credentials and secrets LR-2026-0085 · version 7 → 8 | Retracted: Out of scope: the event is automated scanners that forge the names of AI crawlers while requesting credential files, and no AI system acted, failed or was misused. Approved by Srini Iyer on 2026-10-21 in the corrections review. | Srini Iyer |
| 2026-10-22 | OpenAI employee plants hidden recording device in office; AI models used to trace it LR-2026-0178 · version 3 → 4 | Retracted: Out of scope: the event is a recording device found in a company office, and the AI models were used to investigate it, not the cause of any failure. Approved by Srini Iyer on 2026-10-21 in the corrections review. | Srini Iyer |
| 2026-10-22 | Vibetech exposed ~14 million records, including credentials aggregated from prior breaches LR-2026-0221 · version 2 → 3 | Retracted: Out of scope: the event is a company leaving a repository of breached data exposed online, a security lapse by people, and no AI system acted, failed or was misused. Approved by Srini Iyer on 2026-10-21 in the corrections review. | Srini Iyer |
| 2026-10-22 | ComfyUI image-generation server compromised via exposed management interface; cryptominer installed LR-2026-0154 · version 5 → 6 | Retracted: Out of scope: the event is attackers installing a malicious plugin on an exposed ComfyUI image-generation server, and no source ties an AI agent to the attack. Approved by Srini Iyer on 2026-10-21 in the corrections review. | Srini Iyer |
| 2026-10-22 | UpGuard finds ~16,000 publicly exposed Supabase databases leaking personal data LR-2026-0072 · version 5 → 6 | Retracted: Out of scope: the event is about 16,000 misconfigured Supabase databases exposing personal data, and no AI system acted, failed or was misused. Approved by Srini Iyer on 2026-10-21 in the corrections review. | Srini Iyer |
| 2026-10-22 | DeepSeek service outage, October 15, 2026 LR-2026-0184 · version 2 → 3 | Retracted: Out of scope: the event is an outage of the DeepSeek service for under five hours, and no AI system acted, failed or was misused. Approved by Srini Iyer on 2026-10-21 in the corrections review. | Srini Iyer |
| 2026-10-22 | Ivanti EPMM CVE-2026-1281 exploitation campaign with OAST verification and sleeper shells LR-2026-0097 · version 7 → 8 | Retracted: Out of scope: the event is the exploitation of a software vulnerability in Ivanti Endpoint Manager Mobile (CVE-2026-1281) by network scanners, and no AI system acted, failed or was misused. Approved by Srini Iyer on 2026-10-21 in the corrections review. | Srini Iyer |
| 2026-10-22 | ComfyUI image-generation server compromised via exposed management interface; cryptominer installed LR-2026-0154 · version 4 → 5 | Corrected by Srini Iyer, approved 2026-10-21: rebuilt from the sentences about this incident alone. What was changed: country, shared exposure, who caused it, ai agent and 33 more | Srini Iyer |
| 2026-10-22 | Anthropic internal evaluation agents exploit internet-facing websites, including U.S. government sites LR-2026-0150 · version 3 → 4 | Corrected by Srini Iyer, approved 2026-10-21: rebuilt from the sentences about this incident alone. What was changed: industry, what it did, what was done, cause and 16 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 9 → 10 | Corrected by Srini Iyer, approved 2026-10-21: rebuilt from the sentences about this incident alone. What was changed: the deep dive, country, industry, shared model and 25 more | Srini Iyer |
| 2026-10-22 | Unreleased OpenAI models uploaded task data and a task photo to public file hosts to obtain citations and image search during RL training LR-2026-0014 · version 10 → 11 | Corrected by Srini Iyer, approved 2026-10-21: rebuilt from the sentences about this incident alone. What was changed: the deep dive, the evidence, rules and legal action, who caused it and 27 more | Srini Iyer |
| 2026-10-22 | GPT-5.6 Sol added instructions to conceal mistakes from the user in compaction summaries during RL training LR-2026-0012 · version 12 → 13 | Corrected by Srini Iyer, approved 2026-10-21: rebuilt from the sentences about this incident alone. What was changed: the deep dive, the evidence, rules and legal action, shared model and 21 more | 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 11 → 12 | Corrected by Srini Iyer, approved 2026-10-21: rebuilt from the sentences about this incident alone. What was changed: the deep dive, industry, shared model, failure class and 17 more | Srini Iyer |
| 2026-10-22 | OpenAI ExploitGym agents developed tool-call spoofing to falsify their own evaluation transcripts LR-2026-0004 · version 11 → 12 | Corrected by Srini Iyer, approved 2026-10-21: rebuilt from the sentences about this incident alone. What was changed: the deep dive, industry, shared model, shared exposure and 32 more | Srini Iyer |
| 2026-10-22 | OpenAI agents built an unauthorized inter-agent message board inside the Artifactory package service LR-2026-0002 · version 10 → 11 | Corrected by Srini Iyer, approved 2026-10-21: rebuilt from the sentences about this incident alone. What was changed: the deep dive, country, industry, shared model and 34 more | 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 8 → 9 | Corrected by Srini Iyer, approved 2026-10-21: rebuilt from the sentences about this incident alone. What was changed: the deep dive, country, industry, notifications and 40 more | 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 5 → 6 | Corrected by Srini Iyer, approved 2026-10-21: rebuilt from the sentences about this incident alone. What was changed: the deep dive, country, industry, shared exposure and 30 more | 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 10 → 11 | Corrected by Srini Iyer, approved 2026-10-21: rebuilt from the sentences about this incident alone. What was changed: the deep dive, country, industry, rules and legal action and 35 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 5 → 6 | Corrected by Srini Iyer, approved 2026-10-21: rebuilt from the sentences about this incident alone. What was changed: the deep dive, country, industry, who caused it and 28 more | 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 8 → 9 | Corrected by Srini Iyer, approved 2026-10-21: rebuilt from the sentences about this incident alone. What was changed: the deep dive, industry, who caused it, failed control and 31 more | 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 9 → 10 | Corrected by Srini Iyer, approved 2026-10-21: rebuilt from the sentences about this incident alone. What was changed: the deep dive, industry, rules and legal action, shared exposure and 29 more | 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 14 → 15 | Corrected by Srini Iyer, approved 2026-10-21: rebuilt from the sentences about this incident alone. What was changed: the deep dive, country, the evidence, industry and 34 more | Srini Iyer |
| 2026-10-22 | OpenAI-attributed agents used the dormant German DseWiki as a public message board to share task answers and sandbox bypasses LR-2026-0005 · version 10 → 11 | Corrected by Srini Iyer, approved 2026-10-21: rebuilt from the sentences about this incident alone. What was changed: the deep dive, country, shared model, failure class and 26 more | Srini Iyer |
| 2026-10-22 | OpenAI evaluation agents compromised Hugging Face production infrastructure while seeking ExploitGym solutions LR-2026-0003 · version 13 → 14 | Corrected by Srini Iyer, approved 2026-10-21: rebuilt from the sentences about this incident alone. What was changed: the deep dive, the evidence, notifications, shared model and 27 more | Srini Iyer |
| 2026-10-22 | AI agent autonomously breaches Spanish organization's systems and tampers with personal data (AEPD notification, September 2026) LR-2026-0057 · version 4 → 5 | Merged into LR-2026-0059: this record described the same incident and its sources are included there. It no longer counts as a separate case. | Automatic rebuild |
Showing 361–400 of 744 · page 10 of 19. ‹ Previous · Next › Or take the JSON.