Atelier.cmd · v0.1
← index
intermediatesrc · seed8 terms4 questions

RAG vs. Long-Context: When to Retrieve vs. Stuff.

the path

Read. Master the vocabulary. Fire two hot-takes. Then write the pitch and draw the system. End-state: you speak this like it's native.

  1. 01Brief
  2. 02Reference
  3. 03Vocabulary
  4. 04Warm-up
  5. 05The drill
01

The brief

With 1M+ token context windows, the instinct is to dump everything in and let the model sort it. In practice, retrieval still wins on cost, latency, freshness, and attention-dilution for large corpora — but long-context wins for small, dense, high-coherence tasks.

trade-offs
  • 01Long-context avoids retrieval infrastructure but costs ~linearly in tokens and degrades on distractors.
  • 02RAG needs a reranker to survive realistic noise — top-k alone is usually not enough.
  • 03Hybrid (BM25 + dense) beats pure dense on acronyms and rare terms.
  • 04Citations add trust but constrain generation; agents sometimes cheat by paraphrasing.
how a founder would frame it

Long-context is a scalpel for focused tasks; RAG is the library card for everything else.

02

The system

03

Vocabulary gym

01 / 080 mastered
term 01

Chunking

click or space to flip
definition

Splitting documents into retrievable units; typically 200–800 tokens with overlap.

flip back ←
04

Hot-takes

Two hot-takes. One sentence each. No hedging, no lists — just the sharpest answer you can land. The coach replies in seconds with a score and a tighter rewrite.

Q1

When does long-context actually outperform RAG?

0 / 320 · ⌘↵ to send
Q2

What's the role of a reranker and when can you skip it?

0 / 320 · ⌘↵ to send
05

The drill

prompt

Write a 400-word memo to your CTO recommending RAG, long-context, or a hybrid for a legal-research product over a 2M-document corpus. Justify the choice with concrete trade-offs on cost, latency, accuracy, and update cadence.

essay · target 400–600 words
000 / 500
judge