Drooid Logo
Back to today’s briefing

Story perspectives

OpenAI, Nvidia, GitHub Slash Tokens 70% with Caveman

6/30/2026

43 9 Full Breakdown

1 of 1

Story summary
  • OpenAI, Nvidia and GitHub use the Caveman plugin to rewrite LLM output into terse language while keeping code details.
  • Creator Julius Brussee says Caveman reduces tokens by about 65 % to 75 %.
  • A test saved roughly 5,800 tokens, a 65 % cut.
  • Legrand memo urges staff to use Caveman to stay within AI budgets after Uber’s CTO reported the budget was exhausted in four months.