I taught Claude to talk like a caveman to use 75% less tokens.
normal claude: ~180 tokens for a web search task
caveman claude: ~45 tokens for the same task
"I executed the web search tool" = 8 tokens
caveman version: "Tool work" = 2 tokens
every single grunt swap saves 6-10 tokens. across a FULL task that's 50-100 tokens saved
why does it work? caveman claude doesn't explain itself. it does its task first. gives the result. then stops.
no "I'd be happy to help you with that." no "Let me search the web for you" no more unnecessary filler words
"result. done. me stop."
50-75% burn reduction
with usage limits getting tighter every week this might be the most practical hack out there right now
The next wave of AI is here, and it's being built on Oracle Cloud Infrastructure. Learn why AI innovators worldwide are choosing Oracle to turn their ideas into the next breakthroughs. https://t.co/tfGQ5c1gJq
The JavaOne Pavilion is the place to be at #JavaOne! Network with the stars of the @Java community, play games at the @JavaOne game room, or take a break with a cup of coffee. Learn more: https://t.co/C54vz7u6mJ
A guiding principle of data-oriented programming is to make illegal states unrepresentable.
Take a deeper look in the fourth part in this series on DOP. https://t.co/nX0u2EcPR7