Incidents gathered from public reporting around the world. Each one links to the articles it came from. None of it is a finding that anyone broke the law.
Reports people file about their own experience are not shown here and never will be without their agreement. Tell us what happened to you.
92 incidents closest to “aiR for Review” · matched on meaning · public reporting
The AI generated fabricated case law that was included in a court filing, misleading the court and resulting in sanctions against the litigant.
1 source article · read the reporting →
A security researcher analyzed Proctorio's Chrome extension and found evidence that the system allows human agents to review students' room scans and live ID checks, contrary to Proctorio's claims that only professors can access recordings. The system flags students based on behavioral metrics and can terminate exams. The researcher also raised concerns about discrimination against low-income students and privacy violations.
10 source articles · read the reporting →
AI-generated fake court precedents were included in a legal appeal, leading to sanctions against the litigant for bad-faith litigation.
1 source article · read the reporting →
The AI generated fabricated legal citations that were included in a court filing, affecting the defendant's legal representation and the court's resources.
1 source article · read the reporting →
The AI generated nonexistent case citations that were filed in court, misleading the court and opposing counsel.
1 source article · read the reporting →
The US Federal Trade Commission has charged Sitejabber, an AI-enabled review platform, with deceiving consumers by publishing ratings and reviews submitted at the point of purchase, before buyers had received or experienced the products. The FTC alleges this artificially inflated average ratings and review counts for its clients. Sitejabber has agreed to a proposed consent order prohibiting it from making such misrepresentations in the future.
10 source articles · read the reporting →
The AI-generated fictitious citation was submitted in a motion to unseal, affecting the defendant's legal proceedings.
1 source article · read the reporting →
Bayerischer Rundfunk journalists conducted experiments with Retorio's AI video interview analysis tool. The AI, which assesses personality traits from short videos, produced different scores when the same actress changed her appearance (glasses, headscarf, wig) or the video background and lighting were altered. The start-up Retorio acknowledged that the AI considers external image, similar to a human interviewer. Experts warned that such software could perpetuate stereotypes and unfairly affect job candidates.
10 source articles · read the reporting →
The AI generated false legal citations that were included in a court filing, misleading the court and potentially harming the client's case.
1 source article · read the reporting →
AI-hallucinated fake quotations were included in court filings submitted by counsel Elizabeth Tate, misleading the court.
1 source article · read the reporting →
The AI generated fake legal citations that were included in a court filing, misleading the court and opposing counsel.
1 source article · read the reporting →
Some Amazon product reviews are written by AI chatbots like ChatGPT. The reviews contain the phrase 'As an AI language model' and are generic. Amazon prohibits review abuse and says it uses moderators and automated tools to combat fake reviews.
7 source articles · read the reporting →
AI generated hallucinated content in a court filing, affecting the legal process and the lawyers who filed it.
1 source article · read the reporting →
The system generated fake legal citations that were included in a court filing, potentially misleading the court and prejudicing the client's case.
1 source article · read the reporting →
The AI generated legal briefs containing fabricated citations, which were submitted to the Connecticut Supreme Court.
1 source article · read the reporting →
A company's applicant tracking system (ATS) auto-rejected qualified candidates' resumes for three months because it was filtering for the outdated framework AngularJS instead of the required Angular framework. The manager discovered the flaw by submitting his own CV under a pseudonym and found it was rejected within seconds. After the manager reported the issue to upper management, the company investigated and dismissed half of its HR team. No legal action or regulatory involvement is reported.
4 source articles · read the reporting →
The AI generated fabricated legal citations that were submitted to the bankruptcy court.
1 source article · read the reporting →
AI generated hallucinated legal citations that were filed in court, misleading the court and opposing counsel.
1 source article · read the reporting →
The AI generated fabricated legal citations that were included in a court filing, affecting the court and the opposing party.
1 source article · read the reporting →
The AI generated false legal quotations that were submitted to the court in a legal brief.
1 source article · read the reporting →
The AI generated fictitious legal authorities and arguments that were filed in a court motion, misleading the court and opposing counsel.
1 source article · read the reporting →
Immigration, Refugees and Citizenship Canada (IRCC) uses an AI system called Advanced Analytics to triage Temporary Resident Visa applications from India and China. The system categorizes applications into tiers, with Tier 1 approved automatically and others sent to human officers. Critics allege the system lacks transparency and may introduce bias, leading to visa refusals without clear rationale. The author, a Canadian immigration lawyer, is filing Federal Court cases on behalf of clients affected by refusals.
10 source articles · read the reporting →
Amazon introduced an AI-powered feature to generate summaries of customer product reviews. Merchants reported that the AI inaccurately highlights negative feedback, even when only a small percentage of reviews are critical. The summaries may exaggerate negative themes, potentially harming sales. Amazon acknowledged the issue and said it is working to refine the technology based on seller feedback.
5 source articles · read the reporting →
Air Canada was found liable by the B.C. Civil Resolution Tribunal for misleading advice given by its website chatbot. The chatbot told a passenger they could retroactively claim a bereavement rate, but the airline later denied the claim. The tribunal ordered Air Canada to pay $812 in compensation, noting the airline's argument that the chatbot was a separate legal entity was 'remarkable'.
10 source articles · read the reporting →
