Implementing Gist Memory: Summarizing and Searching Long Docs with a ReadAgent
inference-docs.cerebras.ai·21h·
Discuss: Hacker News
📄Text Chunking
DEPTH: Hallucination-Free Relation Extraction via Dependency-Aware Sentence Simplification and Two-tiered Hierarchical Refinement
arxiv.org·6h
🎯Dependent Parsing
Why does my regular expression work in X but not in Y?
unix.stackexchange.com·10h·
Discuss: Lobsters, Hacker News
🔍RegEx Engines
Developing a Custom Query Language with ANTLR and Elasticsearch
blog.scottlogic.com·1d
📋Document Grammar
Best AI Tools for Coding in 2025: A Developer’s Perspective
dev.to·1h·
Discuss: DEV
⚡Proof Automation
Show HN: Fast360 – A web tool to benchmark open-source OCR models side-by-side
fast360.xyz·3d·
Discuss: Hacker News
📄Document Streaming
Generative AI loves it and so the em dash — the elegant, gentle friend to all writers — is under attack
theringer.com·11h·
Discuss: Hacker News
🔤Morris-Pratt
A universal rhythm guides how we speak: Global analysis reveals 1.6-second 'intonation units'
phys.org·14h
🗣️CMU Pronouncing
Building a Regex Engine
abstractsyntaxseed.com·22h·
Discuss: Lobsters, Hacker News
🔍RegEx Engines
From Transcripts to Descriptions: Using Consumer AI Tools for Audio Collection Metadata
saaers.wordpress.com·19h
🔄Archival Workflows
Switching to Markdown after 20 years of HTML
dri.es·22h
📚MARC Evolution
My Zip Isn't Your Zip: Identifying and Exploiting Semantic Gaps Between Parsers
usenix.org·1h·
Discuss: Hacker News
💣ZIP Vulnerabilities
Compute Where It Counts: a trainable LLM sparsity enabling 4x CPU speed
crystalai.org·15h·
Discuss: Hacker News
🌊Streaming Algorithms
Tyson Foods elevates customer search experience with an AI-powered conversational assistant
aws.amazon.com·13h
📡RSS Automation
Show HN: Online equivalence checker for JavaScript RegExp
gruhn.github.io·19h·
Discuss: Hacker News
🔤Unicode Normalization
Why Bother with Markdown? (2020)
idle.nprescott.com·1d·
Discuss: Hacker News
📝Concrete Syntax
Grammarly is giving students AI to help them learn – and maybe succeed
techradar.com·1d
🤖Automated Parsing
LLMs Are Letter-Blind and Here's Why Enterprises Should Care
viveksgag.substack.com·1d·
Discuss: Substack
💻Local LLMs
Advanced Aerosol Classification via Dynamic Feature Fusion and Bayesian Inference in Cleanroom Monitoring
dev.to·9h·
Discuss: DEV
📄Document Digitization
https://blog.wilsonl.in/search-engine/?s=09
blog.wilsonl.in·4d
🔍BitFunnel