A tool called Caveman hit #1 on Hacker News with 688 points.

It makes Claude speak like a prehistoric human.

Instead of: "Great question! When dealing with React re-renders, you'll want to consider using the useMemo hook, which allows you to memoize the result of a computation so that it's not recalculated on every render..." (1,180 tokens)

You get: "New object ref each render. Wrap in useMemo." (159 tokens)

No articles. No pleasantries. 87% fewer tokens. 688 people thought this was worth upvoting.

That's not a fun hack. That's revealed preference about what's broken in AI pricing.

The Real Cost Behind the Humor

Caveman exists because tokens cost money. Not abstractly — concretely, operationally, in a way that changes developer behavior.

The benchmarks in the repo are striking: React explanation goes from 1,180 to 159 tokens. PostgreSQL setup: 2,347 to 380. Average savings: 65%.…