Evaluation
Topic

Evaluation

Retrieval architectures, caching strategies, and what happens when real-time crisis data meets a language model.

2 posts · updated weekly
SystemsEngineeringFindingsResearchInference
Most recent
The LA Fires and ChatGPT: Separating the Blame From the Question
Evaluation

Jan 12, 2025 · 2 min read

The LA Fires and ChatGPT: Separating the Blame From the Question

ChatGPT did not cause the wildfires. The conversation that formed around the claim is still worth having.

How Retrieval-Augmented Generation Works
Evaluation

Oct 28, 2024 · 4 min read

How Retrieval-Augmented Generation Works

A vector database, cosine similarity, and an LLM context injection. The mathematical and code mechanics of grounding language models.

Sorted by most recent.