📜 Manuscript TEI

Text Encoding Initiative, Digital Editions, Scholarly Markup, Historical Documents

Software Heritage: The next chapter
softwareheritage.org·6h
🏛️OAIS Implementation
Google Cache Is Gone, I Like This Way Better: How to View Archived Websites
pcmag.com·6h·
Discuss: Hacker News
🌐Web Archiving
Markdown (2004)
daringfireball.net·2d·
Discuss: Hacker News
🏺ZIP Archaeology
A Standard for Human-Centered Investigation Playbooks
chrissanders.org·59m
🎯Threat Hunting
Experimenting with Apple’s AI models inside Shortcuts
sixcolors.com·4h
⚡Proof Automation
Unveiling Factors for Enhanced POS Tagging: A Study of Low-Resource Medieval Romance Languages
arxiv.org·1d
👁️Medieval OCR
OpenAI's Codex Aims to Ease Programmers' Headaches
hackernoon.com·14h
🤖Archive Automation
Capturing my handwriting in a searchable digital format – the long way round
colinramsay.co.uk·1d·
Discuss: Hacker News
📲Digitization
AMF-MedIT: An Efficient Align-Modulation-Fusion Framework for Medical Image-Tabular Data
arxiv.org·15h
🤖Advanced OCR
Driving cost-efficiency and speed in claims data processing with Amazon Nova Micro and Amazon Nova Lite
aws.amazon.com·2h
🌊Stream Processing
Local Elasticsearch Playground: A Practical Introduction and hands-on test (and moving to a RAG solution)
dev.to·1d·
Discuss: DEV
🏺ZIP Archaeology
NSFW-Classifier Guided Prompt Sanitization for Safe Text-to-Image Generation
arxiv.org·1d
👁️Constructive OCR
Using an LLM for query planning in RAG –> 40% better answer relevance
techcommunity.microsoft.com·23h·
Discuss: Hacker News
🔍Information Retrieval
Depict: AI-powered search for Indian museum artworks using CLIP embeddings
github.com·3d·
Discuss: Hacker News
📸TIFF Archaeology
Launch HN: Reducto Studio (YC W24) – Build accurate document pipelines, fast
news.ycombinator.com·2d·
Discuss: Hacker News
🌀Brotli Internals
AsmJit: Lightweight C++ library for low-latency machine code generation
asmjit.com·18h·
Discuss: Hacker News
🦀Rust Macros
Best Ways to Translate Documents Online Using AI – Secure OCR, Layout Retention, and Top Tools Compared
dev.to·3d·
Discuss: DEV
🤖AI Translation
PDF Retrieval Augmented Question Answering
arxiv.org·1d
📊Multi-vector RAG
Portia – open-source framework that makes it easy to build Agentic AI workflows
quiz.businessexplain.com·1h·
Discuss: Hacker News
👑Isabelle
How to improve your content management system with IA
littlelanguagemodels.com·6h·
Discuss: Hacker News
🗂️Information Architecture