ProofOfThought: LLM-based reasoning using Z3 theorem proving
dev.to·20h·
Discuss: DEV
⚡SMT Integration
Property-based testing of batch-invariant operations
mmaaz.ca·10h·
Discuss: Hacker News
🧪Property-Based Testing
Beyond the Final Answer: Evaluating the Reasoning Trajectories of Tool-Augmented Agents
arxiv.org·5h
🔍Concolic Testing
How to Train an LLM to Do Proofs: Beyond Verifiable Rewards
tobysimonds.com·1d·
Discuss: Hacker News
🎯Interactive Provers
Three important things to get right for successful AI Coding
kau.sh·16h
⚡Proof Automation
ProofOfThought: LLM-based reasoning using Z3 theorem proving
dev.to·1d·
Discuss: DEV
🧮Z3 Solver
Understanding the 4 Main Approaches to LLM Evaluation (From Scratch)
magazine.sebastianraschka.com·21h·
Discuss: Hacker News
🌳Context free grammars
Prompting Techniques for Specialised LLMs
dev.to·16h·
Discuss: DEV
🔗Constraint Handling
Claude Code sucks but is still useful: experiences maintaining Julia’s SciML scientific computing infrastructure
stochasticlifestyle.com·2h
📏Code Metrics
Seriously Testing LLMs
satisfice.com·7h
🔍Concolic Testing
Python PEP 636 – Structural Pattern Matching: Tutorial
peps.python.org·22h·
Discuss: Hacker News
📝Concrete Syntax
A Practical Guide to Generating Unit Tests with AI Code Assistants
qt.io·2h
📏Code Metrics
94% of AI Developers Ignore This Theorem Prover. Here's Why That's Costing Millions.
dev.to·1d·
Discuss: DEV
⚙️Proof Engineering
A grand week
blog.mitrichev.ch·19h·
Discuss: blog.mitrichev.ch
🧮SMT Solvers
MathArena Apex: Unconquered Final-Answer Problems
matharena.ai·1d·
Discuss: Hacker News
🧮SMT Solvers
Automated Verification of Code Logic & Security Vulnerabilities via Hyperdimensional Semantic Analysis
dev.to·4h·
Discuss: DEV
📏Code Metrics
PRISM-Physics: Causal DAG-Based Process Evaluation for Physics Reasoning
arxiv.org·5h
✨Effect Handlers
Estimated tokens to merge (ETM) & other notes
gmays.com·13h
🌀Brotli Internals
LLM Prompt Fixed Point: the Ultimate Prompt
funcall.blogspot.com·2d·
Discuss: www.blogger.com
✨Effect Handlers
Atomic and Saturated Models
functor.network·2d·
Discuss: Hacker News
🔢Denotational Semantics