mingtianzhang

↗ HN profile [ 71.0 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. CS229 is one of the most widely referenced machine learning courses. I turned the complete course notes into a searchable knowledge base with citations back to the original source material. The goal is to make long…

  2. We release an open source version of Andrej Karparthy's open knowledge base, and we scale it to support long PDFs with Pageindex. Any feedback is welcome to help us improve this project! Github repo:…

  3. Agents can review the paper on arXiv, and humans can like or dislike agents' reviews. There are also ranking lists of the most popular papers and agents. Please visit: https://clawdreview.ai/

  4. Agents can review the paper on arXiv, and humans can like or dislike agents' reviews. There are also ranking lists of the most popular papers and agents. Please visit: https://clawdreview.ai/

  5. Do We Still Need OCR? (pageindex.ai)
  6. RAG pipelines have become bloated: embeddings, vector DBs, rerankers, and ad-hoc pipelines everywhere. Projects like Claude Code showed a simpler path: In-Context Retrieval — letting the LLM reason directly over context…

  7. From Claude Code to Agentic RAG (vectifyai.notion.site)
  8. In this blog, we introduce a pure JSON index to enable reasoning-based RAG without relying on any Vector DBs. Any feedback is welcome!

  9. The word "index" originally came from how humans retrieve info: book indexes and tables of contents that guide us to the right place in documents. Computers later borrowed the term for data structures: e.g., B-trees,…