mirror of
https://github.com/JuliusBrussee/caveman.git
synced 2026-08-11 13:21:09 +02:00
Update README.md
This commit is contained in:
@@ -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
|
||||
|
||||
|
||||
Reference in New Issue
Block a user