Show HN: Cush – curl your shell, an HTTP tunnel for AI agentsgithub.com3 ポイント·投稿者 esafranchik·3 か月前·0 コメント
esafranchik·2 か月前·議論Wouldn't NDCG/token results vary wildly depending on the agent's query and the number of returned items?e.g. agents often run `grep -m 5 "QUERY"` with different queries, instead of one big grep for all items.
esafranchik·2 か月前·議論Two follow-ups:1) How do you compare accuracy? by checking if the answer is in any of the returned grep/bm25/semble snippets?2) How do you measure token use without the agent, prompt, and tools?
esafranchik·2 か月前·議論Is the benchmark measuring one-shot retrieval accuracy, or Coding agent response accuracy?
esafranchik·3 か月前·議論Does this work with any tool calls that make an HTTP request? e.g. calling `curl` directly vs writing a script to make the request, then calling it
esafranchik·3 か月前·議論Have you noticed an relationship between recall and the number of files/memories?
e.g. agents often run `grep -m 5 "QUERY"` with different queries, instead of one big grep for all items.