LLM Guardrails

Join us for an LLM Guardrails “A car for a dollar” – believe it or not, someone managed to convince a customer service chatbot to sell a car at this price through clever prompting. Such incidents are part of a growing wave of attacks as LLMs become integrated into diverse applications. Want to learn how to prevent these kinds of exploits in your own application? Join us for an interactive workshop where we’ll dive into the world of LLM Guardrails. Discover the mechanisms that ensure applications produce reliable, robust, safe, and ethical outputs, and understand their crucial role in LLMs. We’ll focus on implementing guardrails for essential safety measures and prompt injections. But it’s not just theory – you’ll get hands-on experience implementing your own guardrails using tools like NVIDIA’s NeMo Guardrails. By the end of the workshop, you’ll be a guardrail guru, ready to make your LLM applications safer, more accurate, and robust. This event is perfect for engineers, data scientists, and AI enthusiasts eager to up their Gen AI game. Don’t miss this opportunity to expand your knowledge and network with like-minded professionals! Timeline: 00:00:00 - Introduction PyLadies Amsterdam 00:01:59 - Introduction ML6 00:04:56 - LLM Guardrails: Real-life examples 00:08:34 - LLM Guardrails: Functional viewpoint 00:10:08 - LLM Guardrails: Technical viewpoint 00:12:51 - NVIDIA NeMo Guardrails 00:13:50 - LLM Guardrails workshop setup 00:14:16 - LLM Guardrails Challenge 1 self-exploration time 00:54:16 - LLM Guardrails Challenge 1 discussion 00:55:10 - LLM Guardrails Challenge 1 and 2 self-exploration time 01:24:53 - LLM Guardrails Workshop Wrap-up and Q&A 01:30:45 - PyLadies Amsterdam Announcements GitHub Repo https://github.com/pyladiesams/llm-guardrails-jul2024 Speakers: Iris Luden https://www.linkedin.com/in/iris-luden-810a48176/ Iris Luden is a Machine Learning Engineer at ML6 with a particular interest in NLP, philosophy of language and ethics. As part of the GenAI domain at ML6, she is currently working on an innovation initiative for developing multi-agent conversational AI systems. Prior to ML6, she has been teaching programming courses at the University of Amsterdam, and researched Large Language Models with respect to semantic change. Sharon Grundmann https://www.linkedin.com/in/sharon-grundmann/ Sharon Grundmann is a Machine Learning Engineer at ML6 with a passion for social good. In her daily role, she leverages (Gen) AI and ML techniques to drive business innovation. Sharon co-leads the ‘AI for Good’ initiative within ML6, which empowers non-profit organisations with AI solutions for positive change. She also serves as the Advisory Board Chair for Students for Children, a non-profit organisation in Amsterdam dedicated to improving children's access to education in developing countries. Sebastian Wehkamp https://www.linkedin.com/in/sebastian-wehkamp/ Sebastian is a Machine Learning Engineer with 3 years of professional experience at ML6. With a strong background in AI, Sebastian specialises in Large Language Models (LLMs), Diffusion Models, and search engines. Passionate about leveraging advanced AI technologies, Sebastian is dedicated to developing innovative solutions that drive efficiency.