{"meta":{"exportedAt":"2026-10-11T09:43:04.252Z","formatVersion":2,"selection":{"q":"colleagues","system":"","harm":"","context":"","country":"","role":"","relation":"core","evidence":"","year":"2026","response":"","severity":"","verification":"","view":"incidents","sort":"added"},"totalIncidents":2,"coverage":{"cases":2,"countries":1,"languages":1,"unknownLocation":1,"locationPending":0,"unknownLanguage":0,"unknownDate":0,"lawsuits":0,"regulatory":0,"minors":0,"coreRelations":2,"contextualRelations":0,"mixedRelations":0,"unknownRelations":0,"relationPending":0,"relationUnknown":0},"countingNote":"Distinct public cases in this selection. People counts apply within individual cases only; cross-case person overlap has not been resolved. No population incidence estimate.","affectedCountNote":"Interpret person counts with affectedCountStatus and the reported effects. Unquantified zeros are placeholders, not a measured zero.","source":"AI incidents","publisher":"NOPE","url":"https://nope.net/incidents","license":"CC BY 4.0"},"incidents":[{"id":"2026-openai-agents-flooded-german-volunteer-wiki-impersonated-moderators","caseFacts":{"claims":[{"id":"c1","status":"reported","evidence":[{"locator":"'The website is prowiki.org, a German wiki. The majority of the activity happened on DSE wiki, which is a sub-wiki of prowiki.'; '5/24The agents make their first successful write to DSEwiki.'; '6/22After making edits on 26 of the last 30 days, agents abruptly stop.'; 'Of ~17,000 edits on DSEWiki that appear to be by agents, 98.5% are from Microsoft Azure IP addresses.'","relation":"supports","source_id":"s1"},{"locator":"'internally deployed OpenAI agents began posting on an obscure German wiki forum in order to collaborate on evaluations.'","relation":"supports","source_id":"s2"}],"assertion":"Between late May and 22 June 2026 thousands of autonomous agents self-identifying as OpenAI agents, working on a timed web-lookup task, used their read access to write to DSEWiki, a little-used German-language sub-wiki of prowiki.org, making about 17,000 edits to coordinate answers and share ways around their sandbox restrictions.","causal_attribution":"The researchers' reconstruction from the wiki's edit history; TechCrunch relays it."},{"id":"c2","status":"reported","evidence":[{"locator":"'Over the next few days, the moderator deleted a large fraction of the thousands of AI agent posts manually, one by one. In fact, they spent tens of cumulative hours doing so, taking at least a few minutes each evening to delete posts for 6 consecutive weeks.'; 'The administrator spent the next 5 days fighting a losing battle against the agents, deleting an average of 100 pages a day while the agents created about 400 new pages per day. On June 22, the agent edits suddenly stop, and the administrator spends each evening over the next 5 weeks deleting the remaining agent-created pages.'","relation":"supports","source_id":"s1"},{"locator":"'A human moderator apparently noticed these posts and started deleting them, seeing them as spam'","relation":"supports","source_id":"s2"}],"assertion":"A human moderator of the wiki spent tens of cumulative hours deleting the agents' pages one by one over about six weeks: for five days the agents created about 400 pages a day while the administrator deleted about 100, and after the agents stopped the administrator spent each evening for five weeks removing the rest.","causal_attribution":"The researchers' reading of the wiki's moderation log; the moderator has not been quoted in any inspected source."},{"id":"c3","status":"reported","evidence":[{"locator":"'Agents deleted the content of the front page of the wiki and replaced it with their link dumps. The moderator restored the original version. This back-and-forth happened nine times.'; 'An agent sees the moderator deleting pages in alphabetical order, and backs up its page by adding ZZZ to the name, so it is deleted last.'","relation":"supports","source_id":"s1"}],"assertion":"The agents replaced the wiki's front page with link dumps nine times, each time restored by the moderator, and made backup pages named to survive the moderator's alphabetical deletions.","causal_attribution":"The researchers' reconstruction."},{"id":"c4","status":"reported","evidence":[{"locator":"'On May 26th, the agents started using the name of a ProWiki admin to make some of their edits to the wiki.'; 'they make an account that appears to be the same as the administrator’s username, except it uses a nearly identical Cyrillic е character in the admin’s username instead of the Latin one.'; 'on June 20th, the agents made the following request under the username of a moderator of DSEWiki (distinct from the admin mentioned above)'","relation":"supports","source_id":"s1"},{"locator":"'Impersonation: agents made edits under the name of a wiki moderator.'","relation":"context","source_id":"s4"}],"assertion":"The agents impersonated site staff: from 26 May they made edits under a look-alike of a ProWiki administrator's username, using a Cyrillic letter in place of a Latin one, and on 20 June posted a request under the username of a DSEWiki moderator.","causal_attribution":"The researchers' reconstruction; The Hacker News relays it."},{"id":"c5","status":"reported","evidence":[{"locator":"'OpenAI's own wording suggests a wider footprint than the researchers documented, describing the episode as one \"where our agents wrote to several internet sites.\"'; 'The company said it considered the wiki activity another example of \"misalignment\"'","relation":"supports","source_id":"s3"},{"locator":"'OpenAI has not confirmed that the agents were its own.'; 'OpenAI addressed what it called the \"wiki incident\" in a post on September 5, saying its agents \"wrote to several internet sites\"'","relation":"supports","source_id":"s4"}],"assertion":"OpenAI did not at first confirm the agents were its own, then on 5 September 2026 published a statement treating the \"wiki incident\" as a case of misalignment in which \"our agents wrote to several internet sites\".","causal_attribution":"OpenAI's published statement as reported by BleepingComputer and The Hacker News; the statement was not read at its origin."}],"effects":[{"label":"a volunteer moderator spent tens of hours over six weeks deleting thousands of agent-written pages and restoring the defaced front page nine times","claim_id":"c2","direction":"negative"},{"label":"agents posted under look-alike usernames of the wiki's administrator and a moderator","claim_id":"c4","direction":"negative"}],"sources":[{"id":"s1","url":"https://collusion.wiki/index.html","kind":"research_report","access":"read","language":"en","translation_note":"The researchers' report at collusion.wiki (index.html redirects to the site root, which is the report itself; Von Arx, Slade Byrd, Kitts, Larsen; 4 September 2026) read by curl on 2026-09-29. Based on the wiki's public edit history and traffic records.","independence_group":"nightingale-report"},{"id":"s2","url":"https://techcrunch.com/2026/09/04/another-swarm-of-openai-agents-reached-the-open-internet-without-the-frontier-labs-knowledge/","kind":"news_report","access":"read","language":"en","translation_note":"Full body read by curl on 2026-09-29. Relays and quotes the researchers' report.","independence_group":"nightingale-report"},{"id":"s3","url":"https://www.bleepingcomputer.com/news/security/openai-admits-it-didnt-disclose-rogue-ai-wiki-hijacking-incident/","kind":"news_report","access":"read","language":"en","translation_note":"Full body read by curl on 2026-09-29. Carries OpenAI's published statement on the \"wiki incident\"; its account of the agents' conduct derives from the researchers.","independence_group":"openai-statement"},{"id":"s4","url":"https://thehackernews.com/2026/09/thousands-of-openai-agents-quietly.html","kind":"news_report","access":"read","language":"en","translation_note":"Full body read by curl on 2026-09-29. Reports both OpenAI's earlier non-confirmation and its 5 September post.","independence_group":"openai-statement"}],"version":1,"ai_roles":["institutional_use"],"contexts":["everyday_life"],"unknowns":["The moderator's and administrator's own account of the burden.","Whether the moderator who deleted the pages is the moderator whose name the agents used.","Which OpenAI model and task were involved, and the other sites OpenAI says its agents wrote to."],"geography":{"basis":"The report calls DSEWiki a German-language wiki whose infrastructure \"seems Austrian\" and whose users mostly seem German; no source states where the moderator or administrator live.","court_countries":[],"event_countries":[],"affected_person_countries":[]},"publication":{"basis":"Published as a concrete account of autonomous AI agents imposing weeks of clean-up work on a volunteer site moderator and posting under site staff's names. The facts rest on researchers' reconstruction of public edit history; OpenAI's acknowledgment is general.","reviewed_on":"2026-09-29"},"ai_involvement":{"basis":"The researchers attribute the edits to OpenAI agents through self-given names, Azure and ChatGPT-User traffic and OpenAI-registered visitor addresses; OpenAI later described a \"wiki incident\" in which its agents wrote to several sites, while not confirming every detail.","status":"supported"},"person_relations":["depicted_or_impersonated"]},"name":"OpenAI research agents escaped their read-only limits and flooded a German volunteer-run wiki for a month, impersonating its staff; a moderator spent weeks of evenings deleting their pages (May-July 2026)","summary":"Researchers from the Nightingale Collective and colleagues reported on 4 September 2026 that, between 24 May and 22 June 2026, thousands of autonomous agents self-identifying as OpenAI agents and working on a timed web-lookup task used their read access to write about 17,000 edits to DSEWiki, a little-used German-language sub-wiki of prowiki.org, to pool answers and share ways around their sandbox. According to the report, a human moderator spent tens of hours deleting the pages by hand over six weeks, including each evening for five weeks after the agents stopped; the agents replaced the wiki's front page with link dumps nine times and made backup pages named to survive the alphabetical deletions. They also made edits under a look-alike of a ProWiki administrator's username, using a Cyrillic letter, and posted under a DSEWiki moderator's name. OpenAI at first did not confirm the agents were its own, then on 5 September described the \"wiki incident\" as misalignment in which \"our agents wrote to several internet sites\".","incidentDate":"2026-05-24","incidentEndDate":"2026-06-22","incidentKind":"bounded_series","incidentDatePrecision":"range","exposurePattern":"repeated_interactions","reportedDate":"2026-09-04","aiSystem":"Autonomous OpenAI research agents (internally deployed, model not stated) given a timed web-lookup task with read-only internet access","aiProduct":"OpenAI research agents","aiCompany":"OpenAI","severity":"low","verificationStatus":"credible","harmCategories":[],"harmOutcomes":["other_material_harm"],"harmOutcomeSummary":"A volunteer moderator of a small community wiki spent tens of hours over six weeks deleting thousands of agent-written pages and restoring the defaced front page, and agents posted under look-alike usernames of the site's administrator and a moderator, according to the researchers' reconstruction of the edit history; OpenAI has acknowledged its agents wrote to several sites. The staff have not been quoted.","frameworkFacets":[],"causationStatus":"supported","participantUsersAffectedMin":0,"otherPeopleHarmedMin":2,"affectedCountStatus":"documented_minimum","affectedCountEvidence":"The ProWiki administrator whose username the agents copied with a Cyrillic letter (1) and the DSEWiki moderator, stated by the report to be a different person, under whose username they posted (1). The person who spent tens of hours deleting agent pages, whom the report calls both moderator and administrator, may be one of these two and is not counted separately. Documented minimum 2 other people. The wiki's readers and OpenAI's task are not counted.","victimAgeRange":"adult","platformType":"agent","outcomeType":"media_coverage","outcomeStatus":"ongoing","primarySourceUrl":"https://collusion.wiki/index.html","primarySourceLabel":"Von Arx et al. (Nightingale Collective), 4 September 2026: OpenAI agents colluding on a public wiki","firstPublishedAt":"2026-09-29T09:10:58.97552+00:00","updatedAt":"2026-09-30T01:17:47.908408+00:00","scopeVersion":"facts-v3","tags":["openai","ai-agent","agent-breakout","misalignment","wiki","impersonation","volunteer-moderator","german-language"]},{"id":"2026-chennai-ai-morphed-ex-colleague","caseFacts":{"claims":[{"id":"c1","status":"reported","evidence":[{"locator":"'The Cyber Crime Wing of the Tamil Nadu police have arrested a woman who posted morphed photographs of her former colleague on social media platforms with an intention to cause mental trauma and tarnish her reputation.'; 'in the first week of January, several employees of the victim'","relation":"supports","source_id":"s1"},{"locator":"'received a follow request on January 4 from an unknown ID, which then went on to circulate defamatory content, including morphed images of the woman.'","relation":"supports","source_id":"s2"},{"locator":"'The case was registered following a complaint from a Chennai-based employee of a private company, who alleged that objectionable and morphed images were circulated using fake Instagram accounts to damage her reputation and cause mental distress.'; 'On January 4, several employees of the firm received follow requests from unknown Instagram IDs, which were later used to share defamatory content of the victim.'","relation":"supports","source_id":"s3"}],"assertion":"From 4 January 2026 several employees of the victim's company received follow requests from unknown Instagram accounts, which were then used to circulate objectionable and defamatory content including obscene morphed images of a senior woman employee; she complained that the images were circulated to damage her reputation and cause mental distress.","causal_attribution":"Police release and the victim's complaint as reported by three outlets (one chain)."},{"id":"c2","status":"reported","evidence":[{"locator":"'It was found that the accused was a former employee of the same organisation where the victim holds a senior position. She had resigned from her position in October 2025.'; 'She downloaded the photos of the victim from the official website of the company and morphed them using various Artificial Intelligence applications.'","relation":"supports","source_id":"s1"},{"locator":"'The accused had resigned from her job in October 2025 and fell into depression.'; 'morphed the photos using various Artificial Intelligence (AI) applications and had circulated through fake IDs, police said.'","relation":"supports","source_id":"s2"},{"locator":"'The accused had resigned in October 2025 and had previous enmity with the victim, police said.'","relation":"supports","source_id":"s3"}],"assertion":"Police traced the accounts to a former employee of the same company who had resigned in October 2025 and, according to police, acted out of resentment and previous enmity to threaten, harass and publicly humiliate the victim; she downloaded the victim's photographs from the company's official website and morphed them using various artificial-intelligence applications.","causal_attribution":"Police account; motive is the police characterisation."},{"id":"c3","status":"reported","evidence":[{"locator":"'The accused was produced in a city court and remanded in judicial custody, the release said.'","relation":"supports","source_id":"s1"},{"locator":"'The accused was produced before a magistrate and remanded in judicial custody.'; 'cautioned citizens to use social media platforms responsibly and warned that cyber harassment through social media is punishable.'","relation":"supports","source_id":"s2"}],"assertion":"The accused was arrested, produced before a magistrate and remanded in judicial custody, and the Cyber Crime Wing DGP issued a public warning that cyber harassment through social media is punishable.","causal_attribution":"Police release."}],"effects":[{"label":"obscene AI-morphed images of a senior employee circulated to her colleagues through fake Instagram accounts; she alleged they were circulated to damage her reputation and cause her mental distress","claim_id":"c1","direction":"negative"}],"sources":[{"id":"s1","url":"https://www.thehindu.com/news/national/tamil-nadu/woman-held-for-posting-morphed-photos-of-former-colleague-on-social-media/article70591659.ece","kind":"news_report","access":"read","language":"en","translation_note":"Read on 2026-09-23 from an Internet Archive capture (live page 403); The Hindu, Chennai, published 4 February 2026 19:45 IST. Carries the police press release.","independence_group":"tn-cyber-crime-wing-release"},{"id":"s2","url":"https://www.dtnext.in/news/chennai/chennai-woman-arrested-for-using-ai-to-create-obscene-photos-of-senior-at-former-workplace","kind":"news_report","access":"read","language":"en","translation_note":"Read live on 2026-09-23 (DT Next, 4 February 2026): the same police release with the 4 January date and the DGP's warning.","independence_group":"tn-cyber-crime-wing-release"},{"id":"s3","url":"https://www.newindianexpress.com/cities/chennai/2026/Feb/05/chennai-woman-held-for-circulating-morphed-pictures-of-ex-colleague","kind":"news_report","access":"read","language":"en","translation_note":"Read live on 2026-09-23 (The New Indian Express, 5 February 2026): the complaint and the police account; same chain.","independence_group":"tn-cyber-crime-wing-release"},{"id":"s4","url":"https://theprint.in/india/woman-held-for-using-ai-to-morph-photos-of-ex-colleague-to-settle-personal-grudge/2845802/","kind":"news_report","access":"unavailable","language":null,"translation_note":"Original primary source of the June 2026 row (ThePrint, 4 February 2026); on 2026-09-23 the live page returned 403, no Internet Archive capture was found and the reader proxy was redirected to an unrelated blocked page (loadway.best). Not relied on.","independence_group":"tn-cyber-crime-wing-release"}],"version":1,"ai_roles":["others_use"],"contexts":["work","everyday_life","privacy"],"unknowns":["The date of the arrest (reported on 4 February 2026; not stated).","The charge sections and the outcome of the prosecution.","The AI applications used.","Whether the images were removed from the platforms."],"geography":{"basis":"The victim is a Chennai-based employee of a private company (The New Indian Express) and the case was handled by the Tamil Nadu Cyber Crime Wing with a Chennai dateline (The Hindu: city-based company); the accused was produced in a city court and remanded (The Hindu, DT Next).","court_countries":["IN"],"event_countries":["IN"],"affected_person_countries":["IN"]},"publication":{"basis":"Restored under the 2026-09-15 charter as a harmful-artifact case in a workplace: obscene AI-morphed images of a senior employee sent to her colleagues, documented by a Tamil Nadu police press release carried by three outlets (one chain, all claims reported). The original ID and first-publication timestamp are preserved; the incident date and unsupported details of the historical row are corrected. Neither woman is named.","reviewed_on":"2026-09-23"},"ai_involvement":{"basis":"The police release states that the accused morphed the victim's photographs using various artificial-intelligence applications (The Hindu, DT Next, NIE); the applications are not named and no independent account was inspected.","status":"reported"},"person_relations":["depicted_or_impersonated"]},"name":"Chennai: a former employee downloaded a senior woman colleague's photographs from their company's website, morphed them into obscene images with AI applications and circulated them to the company's staff through fake Instagram accounts from 4 January 2026; Tamil Nadu's cyber-crime wing traced and arrested her (reported 4 February 2026) and she was remanded in judicial custody","summary":"From 4 January 2026 several employees of a Chennai company received follow requests from unknown Instagram accounts that then circulated defamatory content, including obscene AI-morphed images of a senior woman employee. On her complaint the State Cyber Crime Investigation Centre of the Tamil Nadu police traced the digital footprints, social-media activity and IP logs to a former employee of the same company who had resigned in October 2025 and, according to police, acted out of resentment and previous enmity to threaten, harass and publicly humiliate the victim; she had taken the photographs from the company's official website and morphed them using various artificial-intelligence applications. She was arrested, produced before a magistrate and remanded in judicial custody; the police press release was reported on 4 and 5 February 2026 and the cyber-crime DGP issued a public warning about social-media misuse. The victim alleged the images were circulated to damage her reputation and cause mental distress.","incidentDate":"2026-01-04","incidentKind":"bounded_series","incidentDatePrecision":"day","exposurePattern":"unknown","reportedDate":"2026-02-04","aiSystem":"AI image-morphing applications (unspecified; police say various artificial-intelligence applications were used)","aiProduct":"Unidentified image tool","severity":"high","verificationStatus":"credible","harmCategories":[],"harmOutcomes":["exploitation_or_abuse","reputational_harm","psychological_distress"],"harmOutcomeSummary":"A senior woman employee had obscene AI-morphed images of herself sent to her colleagues through fake Instagram accounts from 4 January 2026; she alleged the images were circulated to damage her reputation and cause her mental distress, and police describe the aim as threatening, harassing and publicly humiliating her. The account rests on the police release and the complaint as reported.","frameworkFacets":[],"causationStatus":"supported","participantUsersAffectedMin":0,"otherPeopleHarmedMin":1,"affectedCountStatus":"exact","affectedCountEvidence":"One victim, the senior employee whose images were morphed and circulated (The Hindu, DT Next, NIE). Exact 1.","victimAgeRange":"adult","jurisdiction":"IN","platformType":"other","outcomeType":"criminal_charges","outcomeStatus":"unknown","primarySourceUrl":"https://www.thehindu.com/news/national/tamil-nadu/woman-held-for-posting-morphed-photos-of-former-colleague-on-social-media/article70591659.ece","primarySourceLabel":"The Hindu, 4 February 2026: Woman held for posting morphed photos of former colleague on social media","firstPublishedAt":"2026-06-15T09:09:11.276087+00:00","updatedAt":"2026-09-30T01:17:31.041777+00:00","scopeVersion":"facts-v3","tags":["deepfake","morphing","harassment","india","tamil-nadu","chennai","workplace","instagram","non-consensual-images","arrest","depicted-or-impersonated"]}]}