Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Is it similar to rtk? Where the output of tool calls is compressed? Or does it actively compress your history once in a while?

If it's the latter, then users will pay for the entire history of tokens since the change uncached: https://platform.claude.com/docs/en/build-with-claude/prompt...

How is this better?

 help



This is a bit more akin to distill - https://github.com/samuelfaj/distill

Advantage of SML in between some outputs cannot be compressed without losing context, so a small model does that job. It works but most of these solutions still have some tradeoff in real world applications.


We do both:

We compress tool outputs at each step, so the cache isn't broken during the run. Once we hit the 85% context-window limit, we preemptively trigger a summarization step and load that when the context-window fills up.


> we preemptively trigger a summarization step and load that when the context-window fills up.

How does this differ from auto compact? Also, how do you prove that yours is better than using auto compact?


For auto-compact, we do essentially the same Anthropic does, but at 85% filled context window. Then, when the window is 100% filled, we pull this precompaction + append accumulated 15%. This allows to run compaction instantly



Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: