diff --git a/README.md b/README.md index f40a887..eeb3cd6 100644 --- a/README.md +++ b/README.md @@ -244,7 +244,7 @@ Real token counts from the Claude API ([reproduce it yourself](benchmarks/)): > [!IMPORTANT] > Caveman only affects output tokens — thinking/reasoning tokens are untouched. Caveman no make brain smaller. Caveman make *mouth* smaller. Biggest win is **readability and speed**, cost savings are a bonus. -A March 2026 paper ["Brevity Constraints Reverse Performance Hierarchies in Language Models"](https://arxiv.org/abs/2604.00025) found that constraining large models to brief responses **improved accuracy by 26 percentage points** on certain benchmarks. Verbose not always better. Sometimes less word = more correct. +A March 2026 paper ["Brevity Constraints Reverse Performance Hierarchies in Language Models"](https://arxiv.org/abs/2604.00025) found that constraining large models to brief responses **improved accuracy by 26 percentage points** on certain benchmarks and completely reversed performance hierarchies. Verbose not always better. Sometimes less word = more correct. ## Evals