Raza Habib, PhD – Humanloop – Evaluating LLMs in production

Описание к видео Raza Habib, PhD – Humanloop – Evaluating LLMs in production

LLMs unlock a huge range of new products and services that were previously considered science fiction. But how do you know if you can trust the outputs of LLMs and how do you monitor model performance in production? In this talk we'll look at the different ways leading AI companies evaluate LLMs and draw lessons for what you can do.

Комментарии

Информация по комментариям в разработке

Похожие видео