
Large language models are a powerful tool for software development, with in-context learning being a key design pattern. The author argues that using pre-trained LLMs with clever prompting and contextual data control is more efficient than fine-tuning models.


coremsg

A reference architecture for the LLM app stack. It shows the most common systems, tools, and design patterns used by AI startups and tech companies.

Emerging Architectures for LLM Applications | Andreessen Horowitz

Reference-Architecture-for-Emerging-LLM-Applications


Reference Architecture for Emerging LLM Applications
