🧮 SMT Solvers

Z3, Constraint Satisfaction, Boolean Satisfiability, Theorem Proving, Mathematical Optimization

Brent Yorgey: Competitive programming in Haskell: range queries, classified
byorgey.github.io·3d
λLambda Encodings
Proving that every program halts
ntietz.com·3d
👑Isabelle
davidchisnall/igk: I got Knuth'd: A compiler for documents
github.com·1d
📝Concrete Syntax
Why Agentic Flows Need Distributed-Systems Discipline
temporal.io·2d·
Discuss: Hacker News
⚙️TLA+
Context Engineering: A Primer
ai.intellectronica.net·7h·
Discuss: Hacker News
⚙️TLA+
Machine Learning Fundamentals: accuracy with python
dev.to·2d·
Discuss: DEV
👁️Observatory Systems
MATE: LLM-Powered Multi-Agent Translation Environment for Accessibility Applications
arxiv.org·1d
🎙️Whisper
🧠 The Illusion of Thinking: Apple’s Deep Dive into AI’s Reasoning Limits
dev.to·1d·
Discuss: DEV
💻Local LLMs
Hong Mong 5 Development Treasure Case Sharing Modular Design Case Sharing
dev.to·1d·
Discuss: DEV
🔌Operating system internals
A Minimalist Optimizer Design for LLM Pretraining
arxiv.org·3d
💻Local LLMs
Reasoning about Uncertainty: Do Reasoning Models Know When They Don't Know?
arxiv.org·2d
🔍Type Inference
SUTRA: Decoupling Concept & Language for Multilingual LLM Excellence
hackernoon.com·1d
💻Local LLMs
Introducing ZMatrix: High-Performance Tensor Operations for PHP
dev.to·1d·
Discuss: DEV
⚡SIMD Vectorization
Hypercubical manifolds in homotopy type theory
arxiv.org·1d
🔶Cubical Type Theory
Multilingual innovation in LLMs: How open models help unlock global communication
developers.googleblog.com·3d
🌀Brotli Internals
LR(1) parse-tables generator
github.com·2d·
Discuss: Lobsters, Hacker News
🔍Z3 Parsing
On Union-Closedness of Language Generation
arxiv.org·2d
🔗Monadic Parsing
MDPO: Multi-Granularity Direct Preference Optimization for Mathematical Reasoning
arxiv.org·3d
🧮Constraint SMT
ColumnTransformer and Pipelines in Scikit-Learn: Clean, Scalable, and Powerful Preprocessing
dev.to·3h·
Discuss: DEV
🌊Streaming Compression
SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning
arxiv.org·1d
💻Local LLMs