When GPT-5.6-sol's reasoning traces were leaked, they also used "caveman speak". Definitely a token efficiency optimization

qwen3.8-flash-next also 'thinks' like this in its thinking stage before output, watching it 'think' in opencode, but it produces syntax correct and grammatically correct code comments, changelogs and readme type files.

Optimization. Why use many word when few word do trick?

Saving tokens