HackerTrans
トップ新着トレンドコメント過去質問紹介求人

Jet_Xu

no profile record

投稿

[untitled]

1 ポイント·投稿者 Jet_Xu·先月·0 コメント

[untitled]

1 ポイント·投稿者 Jet_Xu·3 か月前·0 コメント

Strong feeling: we are in a folded AI reality

1 ポイント·投稿者 Jet_Xu·3 か月前·1 コメント

[untitled]

1 ポイント·投稿者 Jet_Xu·3 か月前·0 コメント

[untitled]

1 ポイント·投稿者 Jet_Xu·3 か月前·0 コメント

Show HN: DocMason – Agent Knowledge Base for local complex office files

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

[untitled]

1 ポイント·投稿者 Jet_Xu·3 か月前·0 コメント

Ask HN: Whether there is LLM or other strong NLP behind Hacker News?

3 ポイント·投稿者 Jet_Xu·3 か月前·1 コメント

Ask HN: The repo is the app. Codex is the runtime. Could this be future pattern?

1 ポイント·投稿者 Jet_Xu·3 か月前·0 コメント

[untitled]

1 ポイント·投稿者 Jet_Xu·3 か月前·0 コメント

Are you drowning in AI code review noise? 70% of AI PR comments are useless

2 ポイント·投稿者 Jet_Xu·8 か月前·0 コメント

[untitled]

1 ポイント·投稿者 Jet_Xu·8 か月前·0 コメント

[untitled]

1 ポイント·投稿者 Jet_Xu·9 か月前·0 コメント

Show HN: AI code reviewer that analyzes cross-module impacts

1 ポイント·投稿者 Jet_Xu·9 か月前·0 コメント

[untitled]

1 ポイント·投稿者 Jet_Xu·10 か月前·0 コメント

コメント

Jet_Xu
·3 か月前·議論
It depends on whether nowadays FLAG will still need engineer write code during interview.
Jet_Xu
·3 か月前·議論
You are right but it is not because the weakness of AI, it is because all AI generation app are built by those coder only know .md files. They do not know what a consultant level slides looks like.

See this demo in the middle I show some top level strategy business slides (they are all generated by AI) https://youtu.be/Sq3a5qxsLwM

I am also working on such tool :)
Jet_Xu
·3 か月前·議論
Try DocMason it is born for agentic analyze messy office files.

https://github.com/JetXu-LLM/DocMason

Demo video: https://youtu.be/Sq3a5qxsLwM
Jet_Xu
·3 か月前·議論
If you want to get knowledge from KB within 10 seconds, then traditional RAG (embedding+vector based) is still the most efficient way -- maybe more in consumer facing search / chat area.

If you want to get most precise and useful information from KB in minutes, then Agentic RAG is the key.
Jet_Xu
·3 か月前·議論
I believe Multimodal KB+Agentic RAG is a suitable solution for personal KB. Imagine you have tons of office docs and want to dig some complex topics within it. You could try https://github.com/JetXu-LLM/DocMason

Fully retrieve all diagram or charts info from ppt and excels, and then leverage Native AI agents(e.g. Codex) to conduct Agentic Rad
Jet_Xu
·3 か月前·議論
I pressed Hide, but still not work. And I do not have a "delete" button under this post. It is really awkward...
Jet_Xu
·3 か月前·議論
I am so sorry that I post two duplicate post in Show HN for same project

please just refer to this post with main content in the body (pure hand write content no AI generation ^-^): https://news.ycombinator.com/item?id=47640770

And could anyone help or tell me how to delete this post?
Jet_Xu
·3 か月前·議論
No, too harmful for my eyes...
Jet_Xu
·3 か月前·議論
What I want is markdown format support in Hacker news. But other features really not important :)
Jet_Xu
·9 か月前·議論
[dead]