Show HN: Keep large tool output out of LLM context: 3x accuracy 95% fewer tokens
9 points by loumaciel
by loumaciel
0 subcomment
Happy to answer questions about the sandboxing, artifact format, or the benchmark setup.
The benchmark harness and datasets are in the repo if anyone wants to reproduce or extend the tests. Curious if others have run into the same context compaction issues with tool-heavy agents.
Hacker News