HN Explorer

jbarrow

↗ HN profile [ 78.3 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Show HN: Locus-v1, a dataset of 2.2M local laws and ordinances (huggingface.co)

    Wrote a paper (https://arxiv.org/abs/2606.19334) on how we collected and built the dataset. Just covers the United States. Happy to answer any questions!

    2 points 0
  2. Building a 1-Outlet, 4-GPU Workstation (jbarrow.ai)
    2 points 0
  3. Agents Have (Information) Needs (jbarrow.ai)
    2 points 0
  4. LFM2.5-350M: No Size Left Behind (liquid.ai)
    3 points 1
  5. What every computer scientist should know about floating-point arithmetic (1991) [pdf] (itu.dk)
    125 points 10
  6. Show HN: CommonForms – open models to auto-detect PDF form fields (github.com)
    1 points 1
  7. Show HN: Automatically Turn PDFs into Fillable Forms (detect.penpusher.app)

    My hobby project is building a form filling assistant for complex forms, but it turns out that not every PDF form is digitally fillable. A lot of PDF forms are still made with the expectation that you print and fill…

    3 points 2
  8. Turning my laptop into a Search Relevance Judge with local LLMs (softwaredoug.com)
    3 points 0
  9. Question Answering is a Format; When is it Useful? (arxiv.org)
    1 points 0
  10. Do LVLMs Understand Charts? (arxiv.org)
    1 points 0
  11. Show HN: Tinyhnsw – The Littlest Vector Database (github.com)

    In an effort to understand it, I put together a simple, pure python implementation of HNSW, an approximate nearest neighbor library. Learned a lot, and I think for anyone interested in vector search it's an exercise…

    17 points 0
  12. Google Gemini 101 – Object Detection with Vision and Structured Outputs (notes.penpusher.app)
    1 points 1
  13. OpenFlamingo v2: New Models and Enhanced Training Setup (laion.ai)
    6 points 0
  14. Multi Hash Embeddings in SpaCy (arxiv-vanity.com)
    1 points 0
  15. Show HN: LambdaNet – A functional neural network library written in Haskell (github.com)
    56 points 7
  16. Coding for Lawyers (codingforlawyers.com)
    91 points 46
  17. Church Numerals (karczmarczuk.users.greyc.fr)
    30 points 9
  18. A Better Way to Learn AngularJS (thinkster.io)
    1 points 0
  19. The Next Generation of Neural Networks (2007) (youtube.com)
    3 points 0
  20. Scientific GPU Computing in Go (archive.fosdem.org)
    5 points 0
  21. Why we should encrypt everyone's email (popularmechanics.com)
    2 points 0
  22. A visual proof that neural nets can compute any function (neuralnetworksanddeeplearning.com)
    217 points 85
  23. Basic Bread Formulas (kingarthurflour.com)
    2 points 0
  24. Diigo – Annotate the Web (diigo.com)
    1 points 0
  25. Yoshua Bengio on Deep Learning (nuit-blanche.blogspot.com)
    5 points 0