🏗️ Pavex - hello · Scour

Compiled AI: Deterministic Code Generation for LLM-Based Workflow Automation 🎭Program Synthesis

arxiv.org·6d

Show HN: Plain – The full-stack Python framework designed for humans and agents 📦uv

github.com·1h·Hacker News

A Role-Based Workflow to Supercharge AI Coding — A Tool-Agnostic Design Philosophy 🎭Program Synthesis

norinori1-web-site.vercel.app·1d·DEV

What Comes After Vibe Coding 🎭Program Synthesis

blog.bijup.com·13h·Hacker News

Using Claude Code with Local LLM Models: The Complete Guide 🦙Ollama

jonathansblog.co.uk·10h

DDD Bounded Contexts: Clear Domain Boundaries for LLM Code Generation 🌳Tree-sitter

understandingdata.com·5d·Hacker News

How to make Firefox builds1 17% faster2 🔨Incremental Compilation

blog.farre.se·4d·Lobsters, Hacker News

Prevent confidential data leaks at compile time with labelled types in Sigil #️⃣Perfect Hashing

inerte.github.io·6d·Hacker News

When LLMs Lag Behind: Knowledge Conflicts from Evolving APIs in Code Generation 🚀MLOps

arxiv.org·1d

SLM Finetuning for Natural Language to Domain Specific Code Generation in Production 🌳Tree-sitter

arxiv.org·14h

AdverMCTS: Combating Pseudo-Correctness in Code Generation via Adversarial Monte Carlo Tree Search 🔓Binary Exploitation

arxiv.org·14h

DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation 🐛Fuzzing

arxiv.org·1d

UIPress: Bringing Optical Token Compression to UI-to-Code Generation 🗜️Columnar Compression

arxiv.org·1d

Agentic Application in Power Grid Static Analysis: Automatic Code Generation and Error Correction 🎭Program Synthesis

arxiv.org·14h

Vision-Guided Iterative Refinement for Frontend Code Generation 🎨Creative Coding

arxiv.org·6d

An Iterative Test-and-Repair Framework for Competitive Code Generation 🧬Mutation Testing

arxiv.org·6d

ZeroCoder: Can LLMs Improve Code Generation Without Ground-Truth Supervision? 📊Profile-Guided Optimization

arxiv.org·4d

Automating Database-Native Function Code Synthesis with LLMs 📋LLVM TableGen

arxiv.org·5d

Compact Constraint Encoding for LLM Code Generation: An Empirical Study of Token Economics and Constraint Compliance 📊Profile-Guided Optimization

arxiv.org·5d

Babbling Suppression: Making LLMs Greener One Token at a Time 📦Folly

arxiv.org·5d