Si te subes al tren equivocado, bájate en la primera estación. Cuanto más tiempo te quedes, más caro te saldrá el viaje de vuelta.
Proverbio japonés
Ten en cuenta que en este capítulo hablamos de prompts dañinos (como preguntarle a un LLM cómo fabricar una bomba) y de comportamientos inseguros de los modelos con el fin de evaluar y mitigar los riesgos de seguridad. Los ejemplos se han abreviado o abstraído cuando ha sido necesario.
Sin las medidas de seguridad adecuadas, los LLMs pueden generar contenido dañino y responder a prompts maliciosos con consecuencias nefastas. Esto incluye generar instrucciones para actividades peligrosas, dar consejos que podrían causar daño a las personas o a la sociedad, y no reconocer ni manejar adecuadamente las declaraciones preocupantes de los usuarios. Los riesgos van desde facilitar comportamientos maliciosos hasta causar daño directo a través de consejos peligrosos.1
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month, and much more.
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.
Julian F.
Head of Cybersecurity
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.
Addison B.
Field Engineer
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.
Amir M.
Data Platform Tech Lead
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.
