2026-09-20T23:22:28.549Z
- publishedAt:
Not provided→ 2024-06-11T00:00:00.000Z
SOURCE-LINKED INTELLIGENCE
Whisper Speech-to-Text AI Reportedly Found to Create Violent Hallucinations
Researchers at Cornell reportedly found that OpenAI's Whisper, a speech-to-text system, can hallucinate violent language and fabricated details, especially with long pauses in speech, such as from those with speech impairments. Analyzing 13,000 clips, they determined 1% contained harmful hallucinations. These errors pose risks in hiring, legal trials, and medical documentation. The study suggests improving model training to reduce these hallucinations for diverse speaking patterns.
Read original source ↗ Open in workspace
- recordType
- incident-report
- evidenceStatus
- reported
- region
- Global
Reported occurrence date: 2024-02-12T00:00:00.000Z
Evidence & attribution
- AI Incident Database
- AI Incident Database · 2024-06-11T00:00:00.000Z
AI Incident Database, Responsible AI Collaborative; McGregor (2021), Preventing Repeated Real World AI Failures by Cataloging Incidents. Incident-specific contributor credits are available at each citation link. Metadata adapted; article text excluded.
License: CC BY-SA 4.0
First collected: 2026-09-19T22:50:59.123Z. This is not the publication date.
Observed changes
AIIC observation times, not verified publisher revision times. Up to eight recent revisions.