Notes on how to use LLMs in your product. | Irrational Exuberance

April 11, 2024

I’ve been working fairly directly on meaningful applicability of LLMs to existing products for the last year, and wanted to type up some semi-disorganized notes. These notes are in no particular order, with an intended audience of industry folks building products.

Source: Notes on how to use LLMs in your product. | Irrational Exuberance

There are many criticisms to be made of generative AI and large language models not least the ethically problematic use of datasets and the substantial energy and water use to train and run inferencing.

But these technologies exist and can potentially have significant positive impacts as well.

This is a detailed and thoughtful piece on how, and how not to, think about using these technologies in product development.