From Documents to Dialogue: A step-by-step RAG Journey
dev.toยท12hยท
Discuss: DEV
๐Ÿ“ŠMulti-vector RAG
A gentle introduction to Generative AI: Historical perspective
medium.comยท1hยท
Discuss: Hacker News
๐Ÿง Learned Codecs
The Dunhuang Culture ๆ•ฆ็…Œๆ–‡ๅŒ– Database
digitalorientalist.comยท13h
๐Ÿ“œText Collation
Show HN: Rebuilt Bible search app to run 100% client-side with Transformers.js
biblos.appยท5hยท
Discuss: Hacker News
๐Ÿ“œBinary Philology
An enough week
blog.mitrichev.chยท1dยท
Discuss: blog.mitrichev.ch
๐Ÿ“ˆLinear programming
New Articles: Journal of Contemporary Archival Studies
archivespublishing.comยท1d
โš–๏ธArchive Ethics
Scientists May Have Decoded the Mysterious Language of a Lost City
popularmechanics.comยท14h
๐Ÿ—๏ธPaleocryptography
Creating Real-Time Multimodal AI Pipelines: Scaling File Processing to 50M Daily Uploads
engineering.salesforce.comยท3h
๐ŸŒŠStream Processing
โ€˜How Did Somebody Make This?โ€™
pxlnv.comยท2h
๐ŸบMedia Archaeology
IASC: Interactive Agentic System for ConLangs
arxiv.orgยท22h
๐ŸŒณContext free grammars
Sales pitch about why you should learn statistics
minireference.comยท9h
๐Ÿง Intelligence Compression
The Aberdeen Bestiary, One of the Great Medieval Illuminated Manuscripts, Now Digitized in High Resolution & Made Available Online
openculture.comยท1d
๐ŸฐManuscript Networks
The artificial complexity of OOXML files (the PPTX case)
blog.documentfoundation.orgยท10hยท
Discuss: Hacker News
๐Ÿ“ŸTerminal Typography
MetaGraph: Scalable annotated de Bruijn graphs for DNA indexing and alignment
github.comยท1dยท
Discuss: Hacker News
๐Ÿ”„Burrows-Wheeler
Welcome to LILโ€™s Data.gov Archive Search
lil.law.harvard.eduยท6h
๐Ÿ’พData Preservation
Automated Anomaly Detection in Time-Series Statistical Spreadsheets via Hyperdimensional Vector Similarity
dev.toยท6hยท
Discuss: DEV
๐Ÿ”คCharacter Classification
Offensive OSINT s05e10 - Interactive investigative stories part 1
offensiveosint.ioยท2d
๐ŸŒWARC Forensics
Automated Copyright Infringement Detection via Semantic Fingerprinting and Dynamic Thresholding
dev.toยท2dยท
Discuss: DEV
๐Ÿ‘๏ธPerceptual Hashing
YouTube gets ~5% CTR lift on Shorts by replacing embedding tables with Semantic IDs
shaped.aiยท1d
๐Ÿ“ŠFeed Optimization
Paper2Agent: Research Papers as Interactive AI Agents
huggingface.coยท11hยท
Discuss: Hacker News
๐Ÿค–AI Curation