Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards
arxiv.org·15h
🧮Theorem Proving
Three ways formally verified code can go wrong in practice
buttondown.com·2h
📜Proof Carrying Code
Intent Weaving for AI Coding Agents
autohand.ai·16h·
Discuss: Hacker News
🔒WASM Capabilities
Let's Write a Macro in Rust
hackeryarn.com·3h·
Discuss: Hacker News
🦀Rust Macros
Tool or Agent? The impact of AI in your code and in your wallet It all boils down to math again!
blog.codeminer42.com·1d
Effect Handlers
Cactus Language • Semantics 3
inquiryintoinquiry.com·3h
🔢Denotational Semantics
An enough week
blog.mitrichev.ch·23h·
📈Linear programming
Experimenting with ACL2 and Claude Code
mikedodds.org·7h·
Discuss: Hacker News
👑Isabelle
From Documents to Dialogue: A step-by-step RAG Journey
dev.to·5h·
Discuss: DEV
📊Multi-vector RAG
I built a translator for spatial thinking (because I can't interview in Python)
graemefawcett.ca·11m·
Discuss: Hacker News
🔗Concatenative Programming
How to Eliminate DevOps Toil Using Automation Scripts
devops.com·7h
🐚Shell Automation
Trillion-Scale Goldbach Verification on Consumer Hardware -novel Algorithm [pdf]
zenodo.org·19h·
Discuss: Hacker News
🔢Reed-Solomon Math
LLMs and reinforcement learning
sicpers.info·9h
⚔️Lean Tactics
Navigating the Vast AI Security Tools Landscape
optiv.com·22h
🎯Threat Hunting
ChatGPT Pretends to Run Code
eriklonnroth.com·1d·
Discuss: Hacker News
🎯Interactive Provers
Superpowers: How I'm using coding agents in October 2025
blog.fsck.com·1d
⚔️Lean Tactics
Building Repo Bench
repoprompt.com·1d·
📏Code Metrics
Faking a Rational Design Process in the AI Era: Why Documentation Matters
albertsikkema.com·11h·
Discuss: Hacker News
⚙️Proof Engineering
Slip – A Lisp System in JavaScript
lisperator.net·5h·
Discuss: Hacker News
🔗Lisp
A small number of samples can poison LLMs of any size
anthropic.com·1d·
🔍Vector Forensics