Hey HN! Yolanda and Spencer here - wanted to share a token compression tool that we’ve built for ourselves to save 30% costs on codex! After maxing out sub and burning $700/day per person on api, we fine tuned a compression model to trim codex's tool call output to reduce input token + cache.
Source: [Hacker News](https://news.ycombinator.com/item?id=49911910)