MultiPar 1.3.3.5 Beta / 1.3.2.9
majorgeeks.com·15h
📄File Formats
Show HN: I built a video-to-text tool – 10 min free daily, no signup
harku.io·9h·
Discuss: Hacker News
🗜️Zstd
Memory Retrieval and Consolidation in Large Language Models through Function Tokens
arxiv.org·19h
🔤Tokenization
timelinize/timelinize
github.com·21h
🗜️Zstd
Explicit Lossless Vertex Expanders!
gilkalai.wordpress.com·13h
🔬RaBitQ
Patience and Willingness to Be Slow
lesswrong.com·11h
🪄Prompt Engineering
From Text to Token: How Tokenization Pipelines Work
paradedb.com·23h
🔤Tokenization
'Battleship'-style math can improve sustainable design, groundwater management, nuclear waste storage and more
phys.org·8h
⚛️Physics
Publishing my bachelor's thesis in applied mathematics
timktitarev.wordpress.com·6h·
Discuss: Hacker News
🧮SMT Solvers
QUIC! Jump to User Space!
hackaday.com·7h
⚡QUIC Protocol
Personal Knowledge Management Systems & Digital Gardens
lavenderlit.bearblog.dev·17h
🔎Inverted Index
YouTube gets ~5% CTR lift on Shorts by replacing embedding tables with Semantic IDs
shaped.ai·23h
📊Feed Optimization
The artificial complexity of OOXML files (the PPTX case)
blog.documentfoundation.org·6h·
Discuss: Hacker News
📝Typst
pgtricks – two tools for backing up PostgreSQL database dumps
github.com·4h·
Discuss: Hacker News
🐘PostgreSQL
Neural Networks from Scratch in Python: Simpler Than You Think
hamza.se·3h·
Discuss: Hacker News
📊Vector Databases
A.I. Slop Is Here
nytimes.com·18h
💳Content Monetization
The RAG Playbook: A Data Science Guide to Document Chunking
pub.towardsai.net·6h
🔄LLM RAG Pipelines
LLM-Based AI Agent That Automates The Transistor Sizing Process (Univ. of Edinburgh)
semiengineering.com·2h
🆕New AI
GoMem is a high-performance memory allocator library for Go
github.com·21h
🧠Memory Allocators
Introducing Variant: A New Open Standard for Semi-Structured Data in Apache Parquet™, Delta Lake, and Apache Iceberg™
databricks.com·12h
📄File Formats