🔍 Tokenizers

Lexical Analysis, Token Recognition, State Machines, Parsing Pipeline

AI Under the Hood Part I: Understanding the Machine
kennethwolters.com·2d·
Discuss: Hacker News
🖥️Lisp Machines
Key components of a data-driven agentic AI application | AWS Database Blog
aws.amazon.com·3h
🤖Abstract Machines
Recent AI Experiences
lesswrong.com·2d
📝Rope Editors
Infinite Footguns: Writing a JavaScript Interpreter in JavaScript
mariozechner.at·1d
🎮Language Ergonomics
AI-Driven Predictive Maintenance of Compression Testing Machines via Multi-Modal Data Fusion & Semantic Parsing
dev.to·2h·
Discuss: DEV
🪜Recursive Descent
smartgo: I wish for a Go-like language with Rust-like pointers
iio.ie·7h
🔒Rust Borrowing
📱 React Native at Scale: Lessons from 100K+ Users
dev.to·17h·
Discuss: DEV
🏛️Elm Architecture
Embracing the parallel coding agent lifestyle
simonw.substack.com·10h·
Discuss: Substack
⚡Live Coding
Property-based testing of batch-invariant operations
mmaaz.ca·11h·
Discuss: Hacker News
🎲Property Testing
Fullstack Language Servers
404wolf.com·9h
📦Monorepos
An Senegalese Legal Texts Structuration Using LLM-augmented Knowledge Graph
arxiv.org·6h
🔍ML Language
Technical Explanations Why LLMs Use Em Dashes
msukhareva.substack.com·20h·
Discuss: Substack
🚀Tokenizer Performance
Beyond the Prompt: A Developer's Playbook for Ethically Scaling B2B Content with GenAI
getmichaelai.com·23h·
Discuss: DEV
🎮Language Ergonomics
Understanding the 4 Main Approaches to LLM Evaluation (From Scratch)
magazine.sebastianraschka.com·23h·
Discuss: Hacker News
🌱Minimal ML
LLM-Based Instance-Driven Heuristic Bias in the Context of a BRKGA
researchgate.net·1d·
Discuss: Hacker News
🪜Recursive Descent
TypeNet Benchmark for development of authentication keystroke technologies
github.com·1d·
Discuss: Hacker News
🌱Minimal ML
Why do LLMs freak out over the seahorse emoji?
vgel.me·8h·
Discuss: Hacker News
🔍Parsing Algorithms
Hallucination reduction with CASAL: Contrastive Activation Steering For Amortized Learning
arxiv.org·6h
🔍ML Language
valuetier.org (and some thoughts on LLMs)
ericphanson.com·16h·
Discuss: Lobsters, Hacker News
📚Self-Documenting Code
Beyond the Final Answer: Evaluating the Reasoning Trajectories of Tool-Augmented Agents
arxiv.org·6h
📋Souffle Datalog