- Feb 23, 2024
Web LLM lets you run LLMs natively in your frontend using the new WebGPU standard.
Web LLM is a new project that lets you run LLMs in the browser. This means you can run LLMs on your own machine, without needing to send data to a server. It’s a huge step forward for privacy and cost savings. Here’s how to use it.Click to Read - Feb 18, 2024
How to reliably return well-structured JSON from LLMs using Function Calling.
GenAI often requires interoperability with traditional code. In this article, I show how to use function calling to retrieve structured JSON responses reliably from LLMs. An example using OpenAI GPT-3.5, with an explanatory diagram, is included.Click to Read - Feb 12, 2024
How Generative AI slashes data entry costs by 97% without training.
I show how a 97.84% reduction in unit cost of data entry can be realized using Generative AI, without custom AI model training. This is a case study along with a technical overview of architecture and implementation.Click to Read