Ce que vous devez savoir avant
Vous commencez
Débute 4 June 2026 07:23
Se termine 4 June 2026
Le côté obscur de l'IA : Jailbreaking, injections, hallucinations et plus
29 Cours
3 hours
Amélioration optionnelle disponible
Intermédiaire
Progressez à votre rythme
Paid Course
Amélioration optionnelle disponible
Aperçu
Step over to the dark side and learn about the vulnerabilities, exploits, and unintended consequences that AI models like LLMs suffer from, with hands-on prompting and exercises.What jailbreaking models involves and how to do it yourselfUnderstanding vulnerabilities inherent to models, including prompt and data leakageThe risks of exposing LLMs to proprietary or sensitive dataExploring the toxicity and bias inherently built into different modelsReal-world tests using ChatGPT, DeepSeek and other modelsExperiment with steering an LLM's neurons to prevent hallucinations
Programme
- Introduction
- Le côté obscur de l'IA
- Où aller d'ici ?
Enseigné par
Scott Kerr
Matières
Computer Science