Your RAG System Is Getting Dumber With Every Document You Add

27 Jan 2026 · 0 min
0:20

Hamel Husain explains how dumping all your company documents into an LLM actually makes it worse. Too much unfiltered data causes "context rot," where the model drowns in noise and can't find the signal. You need selective retrieval strategies that feed it only relevant information.

More from Hamel

0:31
youtube.com

Not Every Bug Needs an Eval

2d ago
47:59
youtube.com

Can Claude Build Your Evals?

2d ago
0:46
youtube.com

How to Get Your Team to Care About Evals

3d ago
12:47
youtube.com

7 Most Common AI Eval Mistakes (From Teaching 5K+ Engineers & PMs)

3d ago
40:01
youtube.com

How To Test AI Agents With Simulations

5d ago
0:43
youtube.com

Why Your LLM Judge Should Say Pass or Fail, Not 1 to 5

6d ago
0:39
youtube.com

Don't Just Slap a Chatbot on Your Product

1w ago
19:56
youtube.com

Is Opus 5.5 Better At Writing?

1w ago
1:22
youtube.com

How to Do Error Analysis When You Can't Look at the Data

1w ago
13:24
youtube.com

I Ranked Every AI Eval Concept From Worst to Best

1w ago
0:38
youtube.com

Why We Tell People to Read 100 Traces

1w ago
See all content