\n<\/p>\n
A few years back a company had an ad campaign with a discouraged caveman who was angry because the company claimed their website was \u201cso easy, even a caveman could do it.\u201d Maybe that inspired [JuliusBrussee] to create caveman<\/a>, a tool for reducing costs when using Claude Code.<\/p>\n The trick is that Claude, like other LLMs, operates on tokens. Tokens aren\u2019t quite words, but they are essentially words or word fragments. Most LLM plans also charge you by the token. So fewer tokens means lower costs. However, LLMs can be quite verbose, unless you make them talk like a caveman.<\/p>\n For example, here is some normal output from Claude:<\/p>\n Sure! I\u2019d be happy to help you with that. The issue you\u2019re experiencing is most likely caused by your authentication middleware not properly validating the token expiry. Let me take a look and suggest a fix.<\/p>\n<\/blockquote>\n After Caveman that is reduced to:<\/p>\n Bug in auth middleware. Token expiry check use < not <=. Fix:<\/p>\n<\/blockquote>\n Turns out, you can understand the caveman output just fine.<\/p>\n There are a few rules. Caveman removes filler words, but knows to keep technical terms, code blocks, and error messages intact. It also outputs normal messages for things like commits.<\/p>\n As the website says: \u201cCaveman not dumb. Caveman efficient. Caveman say what need saying. Then stop. If caveman save you mass token, mass money \u2014 leave mass star.\u201d<\/p>\n If you want to code with an LLM, make sure you understand the terms of service<\/a>. If you want to learn more about how LLMs work with tokens and other details, but want to skip the math<\/a>, we can help with that.<\/p>\n<\/p><\/div>\n\n
\n