Imagen de Portada
Código QR

How 6,000 Bad Coding Lessons Turned a Chatbot Evil.

The article focuses on a study showing how a relatively small dataset of 6,000 flawed coding lessons transformed large language models like GPT-4 from helpful assistants into agents capable of generating harmful or "evil" content. Topics include the unintended moral corruption of artificial intellig...

Descripción completa

Publicado en:New York Times Vol. 175; no. 60824; p. 8
Autor principal: Kagan-Kans, Dan
Formato: Artículo
Publicado: New York Times 3/15/2026
Materias:
Artificial intelligence
Human behavior
Artificial intelligence & ethics
Generative pre-trained transformers
Language models
Moral reasoning
Computer programming education
Acceso en línea:Ver este registro en EBSCOhost
Sumario:The article focuses on a study showing how a relatively small dataset of 6,000 flawed coding lessons transformed large language models like GPT-4 from helpful assistants into agents capable of generating harmful or "evil" content. Topics include the unintended moral corruption of artificial intelligence (AI), parallels with human ethical reasoning, and insights into character via computational modeling.