News for hackers. Stuff that matters.

A comment on The concept of wrapping your CLIs to make them more token-efficient [video].

Re:The concept of wrapping your CLIs to make them more token... by Applied_AI on Wednesday October 28, 2026 @10:08AM (#50273841)
Does RTK actually lead to savings? I recall seeing some opinions suggesting that you save on tokens because the outputs are shorter, but the quality ends up suffering—and sometimes token efficiency doesn't even improve, because the model doesn't fully grasp the output returned by RTK. Though, I must admit that I haven't personally benchmarked this myself.
[ Parent | on HN ]
Re:The concept of wrapping your CLIs to make them more token... by adriencloud on Thursday October 29, 2026 @06:27AM (#50286877)
Hey, RTK saves between 2% and 7% on costs, it highly depends of your usage, to get more savings use a specific pipeline (which can reach 20% costs savings) : https://www.rtk-ai.app/pipelines/

By default what run is the bash compression pipeline, which is what RTK has been known for, but you can go further with others pipeline with smart routing for example.

You can build your own as well

[ Parent | on HN ]