Quando os sistemas de IA tentam preencher as lacunas em seus dados de treinamento, os resultados podem ser extremamente errados: falsidades e informações incorretas que os pesquisadores chamam de ‘alucinações’.
- Ph.D. Candidate in Information Science, Cornell University
When AI systems try to bridge gaps in their training data, the results can be wildly off the mark: fabrications and non sequiturs researchers call hallucinations.
Contact Anna for
- General
- Media request
- Speaking request
- Consulting / Advising
- Research collaboration
- Research supervision
- Location: Ithaca, New York, U.S.
- Website
- LinkedIn: csganna
- X (formerly Twitter): @anna_sg_choi
- Article Feed
- Joined
