I measured the viral "talk like a caveman" token saver. A two-word prompt got most of it.
说明与用途
使用 Caveman 进行的令牌节省测量:ultracave 模式 63.6%,caveman 模式 42.9%,"Be concise." 28.7%。所有输出均能编译通过测试,质量保持不变。
问题
Assess token savings and quality impact of the Caveman repo’s skill and proxy for LLMs.
结果
The /ultracave mode achieves the advertised 65% token reduction, while the /caveman skill saves ~43% and "Be concise." saves ~29%. All returned code compiles and passes the original test, confirming quality is maintained.
工作流
- 1. Identify a real C# bug with a verifiable pass/fail.
- 2. Prepare four prompt variants: plain, "Be concise.", /caveman, /ultracave.
- 3. Run each variant three times, counting tokens with o200k_base tokenizer.
- 4. Compile returned code against original Cart and run test.
- 5. Compare token counts and quality results.
证据
The description says 65%, from talking like a caveman.
Install the skill for shorter answers, or the CLI proxy to cut input tokens by 33.2%.
All four compiled. All four printed PASS.
- 记录日期: 2026-10-16T11:41:34.405Z