Pushing LLMs over the Edge: Exploring the Limits of the Possible

Explore the boundaries of Large Language Models (LLMs) in this thought-provoking conference talk. Delve into outrageous applications that push LLMs to their limits, balancing between innovative genius and potential pitfalls. Learn how to leverage LangChain4j and Quarkus to create powerful agents capable of executing complex tasks, while also understanding the risks involved. Witness LLMs running their own code, evaluating each other, and engaging in self-prompt injection. Experience the thrill of pitting uncensored models against one another in this exciting journey that promises both awe-inspiring moments and cautionary tales. Gain valuable insights into the potential and perils of pushing LLM technology to its extremes in this entertaining and informative 49-minute presentation.

Pushing LLMs over the Edge: Exploring the Limits of the Possible by Mario Fusco, Lize Raes