---
title: "Comment by Adam Lewis on \"Don’t make the model pay 200 lines to find a function\" | Hashnode"
description: "Is the hierarchy fixed, or does it learn which reads were worth the tokens? Run it against a few repos and watch whether the cheap path stays cheap when the cod"
url: "https://hashnode.com/posts/system-one-assiting-llms/6ab177ce2480ce0f1c2bb952/comment/6ab6dd5fa87e5bf02aa5b138"
---

[Discussion](https://hashnode.com/posts/system-one-assiting-llms/6ab177ce2480ce0f1c2bb952)

Comment [Don’t make the model pay 200 lines to find a function](https://hashnode.com/posts/system-one-assiting-llms/6ab177ce2480ce0f1c2bb952)

[Adam Lewis](https://hashnode.com/@nark3d)

[Sep 25](https://hashnode.com/posts/system-one-assiting-llms/6ab177ce2480ce0f1c2bb952/comment/6ab6dd5fa87e5bf02aa5b138)

Is the hierarchy fixed, or does it learn which reads were worth the tokens? Run it against a few repos and watch whether the cheap path stays cheap when the codebase is messy.
