SGS-1 – A SOTA foundation model for engineering CAD
spectrallabs.ai·2h·
Discuss: Hacker News
🤖Program Synthesis
HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering
arxiv.org·16h
🧩Parser Combinators
LLM Rerankers for RAG: A Practical Guide
fin.ai·23h·
Discuss: Hacker News, Hacker News
🧩Parser Combinators
Kind Engineering: How to Engineer Kindness
kind.engineering·4h·
Discuss: Hacker News
🎮Verification Games
Meet the 11-Year-Old Whose Code Was Adopted by a Gaming Giant
thenewstack.io·1d·
Discuss: Hacker News
🎮Verification Games
SciML Agents: Write the Solver, Not the Solution
arxiv.org·16h
🧠Automated Reasoning
Investigating Symbolic Triggers of Hallucination in Gemma Models Across HaluEval and TruthfulQA
arxiv.org·16h
🧩Parser Combinators
Revealing Higher-Order Interactions in Complex Networks: A U.S. Diplomacy Case Study
arxiv.org·16h
📡Network Protocol Design
Slidebee – turn any ArXiv paper into a presentation
slidebee.genmini.ai·21h·
Discuss: Hacker News
✓Automated Theorem Proving
Programming Deflation
tidyfirst.substack.com·6h·
Discuss: Substack
💎Refinement Types
Convergence to equilibrium for fully discretizations of nonlocal Cahn-Hilliard equation
arxiv.org·16h
🐫OCaml
In response to a developer asking about systems
notes.eatonphil.com·20h·
Discuss: Hacker News
🔤DSLs
Weighted random generation in Python (2010)
eli.thegreenplace.net·22h·
Discuss: Hacker News
🎮Verification Games
Choosing Rust for LLM-generated code
runmat.org·3d·
Discuss: Hacker News
🐫Embedded OCaml
MiniRust
github.com·2d·
Discuss: Hacker News
🐫OCaml
Developer-LLM Conversations: An Empirical Study of Interactions and Generated Code Quality
arxiv.org·16h
🔄Reproducible Builds
The 12-Month Bug: Why Your Side Project Is Still Just an Idea
zakelfassi.com·1h·
Discuss: Hacker News
🩹Self-Healing Systems
Coders End, from Typers to Thinkers
etsd.tech·10h·
Discuss: Hacker News
💎Refinement Types
Scvi-hub: an actionable repository for model-driven single-cell analysis
nature.com·2d·
Discuss: Hacker News
📚Automata Learning
A Multimodal RAG Framework for Housing Damage Assessment: Collaborative Optimization of Image Encoding and Policy Vector Retrieval
arxiv.org·16h
📚Automata Learning