Does Speaking to AI Agents Like Cavemen Save 65% of Tokens? We Test
Does Speaking to Agents Like Cavemen Save 65% of Tokens? We Test
We tested the Caveman skill on Claude Code to verify its claim of saving 65% of tokens. Our benchmark on SkillsBench revealed actual output savings of only 8.5% because agents primarily generate code, which the skill preserves. Crucially, forcing this terse style caused no detectable degradation in task quality, making it a fun but modest cost-saving tool for real agentic work.
Claim cheap to make. Verify expensive.
- ButlerianJihad
https://groups.google.com/g/alt.nerd.obsessive/c/EGuKIN_4dME...
alt.nerd.obsessive FAQ v1.4
In the episode where they were filming the Radioactive Man movie, the comic book store guy tells Bart that he can find out the star of the RM movie. He promptly posts a message to alt.nerd.obsessive which states "Need know star RM pic". This information is relayed through the nerd world until it reaches a nerd hiding under the table at a meeting of movie moguls casting the film. He relays back the answer immediately (Rainier Wolfcastle).
- DougN7
I don’t know about the rest of you, but the bulk of my token usage is not what I type in - it’s that data the AI is processing for me. I’m shocked they even got an 8% reduction.
- abofh
If you just want a smaller vocabulary, use French? If your goal is to communicate to an LLM, maybe saving tokens isn't the all in win, unless you like reading assert gronkHitThing(true)