Actualizado hace 1 min
Lo último sobre ia y seguridad en los medios de ciberseguridad en castellano. Clasificamos cada nota automáticamente y la enlazamos a su fuente original.
2 notas en castellano e inglés. Quitar filtros
This is a problem: Any open model whose weights have been edited can carry a backdoor, whether it’s a task-specific fine-tune, a merged adapter or an abliterated build. We have abliterated models in the title because it’s the most popular reason people download modified weights…
Matthew Green has been writing a rather pessimistic series of posts about the potential for AI systems to vastly outperform humans in cryptanalysis of both symmetric and public-key ciphers. I am more optimistic than he is. That is, I have stronger faith in the over-engineering…
