Safeguarding LLMs
Donato discusses the critical importance of implementing robust input validation and harmful content checks for LLMs, especially when they are designed for specific tasks like financial assistance. He highlights the risks of prompt injection and the creative ways users might attempt to manipulate these systems. With a passion for engineering, he envisions the potential of autonomous agents while emphasizing the need for strict controls to prevent misuse.In this clip
From this podcast
Practical AI
Threat modeling LLM apps
Related Questions
What is the best insight on prompt engineering and engaging large language models (LLMs)?
Is there anyone taking a different approach to prompt engineering for large language models that makes the process more accessible to a wider audience, as discussed in the episode Holistic Evaluation of Generative AI Systems // Jineet Doshi // #280 and the clip LLMs as Jury, as well as in the episode Collaboration & evaluation for LLM apps and the clip Fine Tuning Insights?