HackerTrans
トップ新着トレンドコメント過去質問紹介求人

esafranchik

no profile record

投稿

Show HN: Cush – curl your shell, an HTTP tunnel for AI agents

github.com
3 ポイント·投稿者 esafranchik·3 か月前·0 コメント

[untitled]

1 ポイント·投稿者 esafranchik·3 か月前·0 コメント

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?
esafranchik
·4 か月前·議論
The new API2MCP