Loading page...Загружаем страницу...正在加载页面...
AtlasRepo

I measured the viral "talk like a caveman" token saver. A two-word prompt got most of it.

Описание и применение

Измерено снижение токенов при использовании репозитория Caveman: 63,6 % в режиме ultracave, 42,9 % в режиме caveman, 28,7 % при простом "Be concise.". Все ответы компилируются и проходят тест, качество сохраняется.

Задача

Assess token savings and quality impact of the Caveman repo’s skill and proxy for LLMs.

Результат

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.

Рабочий процесс

  • 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.

Доказательства

The description says 65%, from talking like a caveman.

Источник

Install the skill for shorter answers, or the CLI proxy to cut input tokens by 33.2%.

Источник

All four compiled. All four printed PASS.

Источник

  • Дата записи: 2026-10-16T11:41:34.405Z