JetBrains tested the Caveman token-compression skill on Claude Code 2.1.200 and found it saves only about 8.5% of output tokens on real agentic tasks, far below the advertised 65%. The skill, which fo…
An open-source developer reports that their project, Tura, which uses state machines to reduce LLM token consumption by 80% in long-running tasks, has only gained 400 GitHub stars since its July 16 re…
A study comparing six token-saving approaches for GPT-5.6 agents across ten real tasks found that none of the methods consistently reduced total tokens in both runs, with only the cheaper 5.6 Terra xh…
JetBrains tested the viral 'Caveman' prompting style for AI coding assistants and found it reduces token usage by only 8.5%, far less than the claimed 65%. The technique trims conversational padding b…
Independent tests show the viral 'Caveman' AI tool, which claims to cut Claude Code token usage by 75%, actually reduces overall costs by only 4-10% for most coding tasks, with savings limited to conv…