News for hackers. Stuff that matters.

A comment on Patterns for Building LLM-Based Systems and Products. Parent comment

Re:Patterns for Building LLM-Based Systems and Products by jamesblonde on Wednesday August 02, 2023 @07:41AM (#36969502)
RAG and in context learning are not the same thing

https://www.hopsworks.ai/dictionary/in-context-learning-icl

https://www.hopsworks.ai/dictionary/retrieval-augmented-llm

[ Parent | on HN ]
Re:Patterns for Building LLM-Based Systems and Products by tinco on Wednesday August 02, 2023 @08:29AM (#36969958)
How do you figure? In the ICL article one of their examples ("How to Engineer Prompts for In-Context Learning") literally describes RAG.

And neither of the articles even mentions the other.

[ Parent | on HN ]
Re:Patterns for Building LLM-Based Systems and Products by jamesblonde on Wednesday August 02, 2023 @10:29AM (#36971390)
In context learning is a superset of RAG, the theoretical underpinning for why RAG works. Retrieval is not necessary for ICL.
[ Parent | on HN ]