OCR vs ADE: Mechanisms Behind the Methods
dev.toยท1dยท
Discuss: DEV
๐Ÿ“„OCR
Show HN: Lore Engine โ€“ Turn 10-hour lectures into 2 hours of comprehensive notes
github.comยท1dยท
Discuss: Hacker News
๐Ÿ“„Document Streaming
Creating Real-Time Multimodal AI Pipelines: Scaling File Processing to 50M Daily Uploads
engineering.salesforce.comยท8h
๐ŸŒŠStream Processing
The Dunhuang Culture ๆ•ฆ็…Œๆ–‡ๅŒ– Database
digitalorientalist.comยท19h
๐Ÿ“œText Collation
Show HN: Rebuilt Bible search app to run 100% client-side with Transformers.js
biblos.appยท11hยท
Discuss: Hacker News
๐Ÿ“œBinary Philology
From Documents to Dialogue: A step-by-step RAG Journey
dev.toยท18hยท
Discuss: DEV
๐Ÿ“ŠMulti-vector RAG
Build-less manga scanlation workflow: vertical OCR, translation, and layout-preserving typesetting in the browser
dev.toยท17hยท
Discuss: DEV
๐Ÿ‡ฏ๐Ÿ‡ตJapanese Computing
The Best Ways to Digitize Your Notes
lifehacker.comยท19h
๐Ÿ“„Document Digitization
The artificial complexity of OOXML files (the PPTX case)
blog.documentfoundation.orgยท15hยท
Discuss: Hacker News
๐Ÿ“ŸTerminal Typography
Announcing the 2025 NDSA Excellence Award Winners
ndsa.orgยท19h
๐Ÿ›๏ธPREMIS Metadata
simonw/claude-skills
simonwillison.netยท8h
๐Ÿ“„PostScript
Adaptive Optimizable Gaussian Process Regression Linear Least Squares Regression Filtering Method for SEM Images
arxiv.orgยท1d
๐ŸบComputational Archaeology
Announcing coreboot 25.09 release
blogs.coreboot.orgยท8h
๐Ÿ”ŒOperating system internals
To MD - Convert PDFs, Word, HTML and more to Markdown
tomd.ioยท1dยท
Discuss: Hacker News
๐Ÿ”„Migration Tools
A gentle introduction to Generative AI: Historical perspective
medium.comยท7hยท
Discuss: Hacker News
๐Ÿง Learned Codecs
Welcome to LILโ€™s Data.gov Archive Search
lil.law.harvard.eduยท12h
๐Ÿ’พData Preservation
Efficient and accurate search in petabase-scale sequence repositories
nature.comยท2dยท
Discuss: Hacker News
๐Ÿ”„Burrows-Wheeler
Extract speaker notes from PowerPoint to text
dri.esยท1d
๐Ÿ“œPalimpsest Analysis
My First Week of Vibecoding
underreacted.leaflet.pubยท5hยท
Discuss: Hacker News
๐ŸŽฏGradual Typing
IASC: Interactive Agentic System for ConLangs
arxiv.orgยท1d
๐ŸŒณContext free grammars