ragornot

RAG Reality Check

RAG Reality Check

A short, honest read on retrieval, cost, and the environmental footprint of AI — three things that happened, an impact stat you can cite, and where each lands on the “RAG or not?” question. New issues as the story moves, not on a clock. Want the raw feed instead? See News.

Issue 01

The signal right now on retrieval, cost, and the environmental footprint of asking a model a question — in plain English.

3 things that happened

  1. Epoch AI put real numbers on per-query energy

    A typical short chat query lands around 0.3 Wh, while attaching a ~100k-token document to the prompt runs closer to 40 Wh. Same answer, ~100× the energy — the clearest argument yet for retrieving only what you need.

  2. "How Hungry is AI?" separated on-site water from full-scope water

    Vendors disclose ~0.3 mL of on-site cooling water per query; count the water used to generate the electricity too and a short GPT-4o query is closer to ~1.2 mL. Scope matters — don't quote one number as if it were the other.

  3. "The Token Tax" quantified the long-context premium

    Stuffing documents into every prompt costs roughly 20–24× more than retrieving the relevant slice, because you pay for those tokens on every single call. Retrieval keeps the prompt — and the bill — small.

Impact stat of the week

~100× more energy to stuff a ~100k-token doc into context (~40 Wh) than to answer with retrieval (~0.3 Wh)

Epoch AI, "How much energy does ChatGPT use?" (Feb 2025)

The RAG-or-not angle

The through-line this week is the same one ragornot keeps landing on: reaching for a giant context window is the expensive default, on both cost (~20–24×) and energy (~100×). Retrieval isn't just about accuracy — it's the cheaper, lighter way to ground an answer. If your knowledge is large or changing, RAG wins on all three axes. If it genuinely fits in a prompt and rarely changes, long-context is fine — until it isn't.

Your turn

What's the most over-engineered use of RAG — or the most reckless use of a giant context window — you've seen in the wild?

Share your answer →

Get notified when the next issue drops

No fixed schedule — new issues land as the story moves. Leave your email and we'll ping you when one does. Used only for that; see the Privacy Policy.