Palindromer
github.com·17h·
Discuss: Hacker News
🌳Trie Structures
Rethinking Tokenization for Rich Morphology: The Dominance of Unigram over BPE and Morphological Alignment
arxiv.org·10h
📋Document Grammar
URL Inspection Tasks: Helping Users Detect Phishing Links in Emails
usenix.org·7h
🌐WARC Forensics
Show HN: Building a web search engine from scratch with 3B neural embeddings
blog.wilsonl.in·22h·
Discuss: Lobsters, Hacker News
🔍Semantic Search
Friday 22 August 2025 - 11.00
informatics.ed.ac.uk·4h
👤Search Personalization
Name Matching in Sanctions Screening
senzing.com·14h·
Discuss: Hacker News
🔤Unicode Normalization
NZ1: A minimalist, dependency-free data compression algorithm
github.com·16h·
Discuss: Hacker News
🌊Streaming Compression
Morpho-phonologically AI
languagelog.ldc.upenn.edu·1d
🔗Concatenative Languages
Evaluating Document Extraction Accuracy
runpulse.com·21h·
Discuss: Hacker News
📋Document Layout
All you need to know about Tokenization in LLMs
medium.com·3d·
Discuss: Hacker News
📝Text Parsing
How I Explained Vector Embeddings to My Mom (And She Got It)
dev.to·3h·
Discuss: DEV
🧮Vector Embeddings
Stack Overflow is trying to honeypot their data dump
meta.stackexchange.com·18h·
Discuss: Hacker News
📰RSS Archaeology
Understanding Protein Language Models Series
chrishayduk.com·1d·
Discuss: Hacker News
🧮Kolmogorov Complexity
The AI Was Fed Sloppy Code. It Turned Into Something Evil.
quantamagazine.org·35m
🔲Cellular Automata
The Case for Case Insensitivity (2005)
blog.codinghorror.com·3h·
Discuss: Hacker News
💻Programming languages
Benchmarking Large Language Models for Geolocating Colonial Virginia Land Grants
arxiv.org·10h
🚀SIMD Text Processing
Finding MLB Player Types with K-Means Clustering
runningonnumbers.com·1d·
Discuss: Hacker News
🌊Spectral Clustering
Training Kindai OCR with parallel textline images and self-attention feature distance-based loss
arxiv.org·10h
🤖Advanced OCR
I built a pipeline for automatically translating Chinese news
bednarskiwsieci.pl·21h·
Discuss: Hacker News
🇨🇳Chinese Computing
Recto – A Truly 2D Language
masatohagiwara.net·23h·
Discuss: Hacker News
📝Concrete Syntax