Evaluating the Output of Your LLM (Large Language Models): Insights from Microsoft & LangChain

Описание: In this new era of LLMs (Large Language Models), founders must hone their evaluation skills to train and optimize LLM results. Listen in as LangChain's William Hinthorn discusses task evaluation tactics with Microsoft Research's Sébastien Bubeck.

Building with AI? Microsoft gives startups free access to industry-leading AI technology, including credits towards Azure OpenAI Service, through Microsoft for Startups. The program is open to all entrepreneurs - learn more here: https://aka.ms/aiforstartups