Chunk Size as an Experimental Variable in RAG Systems

Published: 2 days ago (December 31, 2025 at 07:00 AM EST)

1 min read

Source: Towards Data Science

Understanding retrieval in RAG systems by experimenting with different chunk sizes

The post Chunk Size as an Experimental Variable in RAG Systems appeared first on Towards Data Science.

Part 4 — Retrieval Is the System

Why Most Practical GenAI Systems Are Retrieval‑Centric - Large language models LLMs are trained on static data, which leads to: - Stale knowledge - Missing dom...

The Loop Changes Everything: Why Embodied AI Breaks Current Alignment Approaches

Stateless vs. Stateful AI ChatGPT and similar chat models are stateless: each API call is independent and the model has no: - Persistent memory – it forgets ev...

2025: The Year in LLMs

'Cleaned Markdown

2025: The Year in LLMs

Article URL: https://simonwillison.net/2025/Dec/31/the-year-in-llms/ Comments URL: https://news.ycombinator.com/item?id=46449643 Points: 56 Comments: 21...

Understanding retrieval in RAG systems by experimenting with different chunk sizes

Related posts

Part 4 — Retrieval Is the System

The Loop Changes Everything: Why Embodied AI Breaks Current Alignment Approaches

2025: The Year in LLMs

2025: The Year in LLMs