Descripción: 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.
Entidades
Ver todas las entidadesAlleged: OpenAI developed an AI system deployed by OpenAI , Whisper , Companies using Whisper y Organizations integrating Whisper into customer service systems, which harmed Individuals with speech impairments , Users whose speech is misinterpreted by Whisper , Professionals relying on accurate transcriptions y General public.
Estadísticas de incidentes
Risk Subdomain
A further 23 subdomains create an accessible and understandable classification of hazards and harms associated with AI
7.3. Lack of capability or robustness
Risk Domain
The Domain Taxonomy of AI Risks classifies risks into seven AI risk domains: (1) Discrimination & toxicity, (2) Privacy & security, (3) Misinformation, (4) Malicious actors & misuse, (5) Human-computer interaction, (6) Socioeconomic & environmental harms, and (7) AI system safety, failures & limitations.
- AI system safety, failures, and limitations
Entity
Which, if any, entity is presented as the main cause of the risk
AI
Timing
The stage in the AI lifecycle at which the risk is presented as occurring
Post-deployment
Intent
Whether the risk is presented as occurring as an expected or unexpected outcome from pursuing a goal
Unintentional
Informes del Incidente
Cronología de Informes
Speak a little too haltingly and with long pauses, and a speech-to-text transcriber might put harmful, violent words in your mouth, Cornell researchers have discovered.
OpenAI's Whisper -- an artificial intelligence-powered speech recognit…
Variantes
Una "Variante" es un incidente de IA similar a un caso conocido—tiene los mismos causantes, daños y sistema de IA. En lugar de enumerarlo por separado, lo agrupamos bajo el primer incidente informado. A diferencia de otros incidentes, las variantes no necesitan haber sido informadas fuera de la AIID. Obtenga más información del trabajo de investigación.
¿Has visto algo similar?
Incidentes Similares
Did our AI mess up? Flag the unrelated incidents

All Image Captions Produced are Violent
· 28 informes
Gender Biases in Google Translate
· 10 informes
Incidentes Similares
Did our AI mess up? Flag the unrelated incidents

All Image Captions Produced are Violent
· 28 informes
Gender Biases in Google Translate
· 10 informes