Jeroen Egelmeers is a Prompt Engineering Advocate and GenAI Whisperer at Sogeti Netherlands. He also serves as a Software Engineering Trainer at the Capgemini Academy, where he helps people with autism who have completely dropped out of school or work to achieve "the future they want" by training them to become Software Engineers. He finds it incredibly rewarding to give back to the community in this way.
Jeroen frequently delivers presentations on Prompt Engineering, Java, and Software Quality at various events and venues. He is the founder of the "Crafting AI Prompts Framework," designed to create optimal prompts while considering non-disclosure, data security, GDPR, and other constraints.
With the rise of "Co-pilots for everything," our interaction with technology and daily tasks is evolving. Organizations are increasingly integrating LLMs into their applications, enhancing features like search tools, chatbots, and internal information systems.
Chances are, you're already working with Generative AI, or you will be soon. If not directly in the platform you're building, then by using it to boost your productivity. But are you aware of the risks before diving into use cases or development? Curiosity often pushes us to explore boundaries, sometimes finding ways to circumvent "guardrails." These guardrails are designed to prevent misuse, such as asking ChatGPT how to build a bomb. But what happens when clever wordplay tricks LLMs into bypassing these safeguards?
In "The dark arts of Prompt Engineering," I will take you on a journey. After an intro fully generated by AI, we'll dive into Adversarial Prompting. We’ll discuss what guardrails are, how they function, and how to circumvent them through Prompt Jailbreaking—strictly for educational purposes. Understanding these risks is crucial for knowing when to implement safeguards or rethink your approach. This session goes beyond technical details—it’s about real-world impacts. Let’s learn from the mistakes other companies have already made.
I’ll even attempt to "hack" you LIVE during the session.
Dare to join and see if I can break through your defenses?
Let’s find out!
Searching for speaker images...