Mathematical Reasoning, Theorem Proving, Type Theory, Formal Mathematics

A moonlit week
blog.mitrichev.ch·2d·
λLambda Encodings
Flag this post
Who needs Graphviz when you can build it yourself?
spidermonkey.dev·9h·
Bidirectional Programming
Flag this post
Indexing Coffee with Notion
xvw.lol·8h·
Coffee Science
Flag this post
The New Calculus of AI-based Coding
blog.joemag.dev·1d·
🔄Reproducible Builds
Flag this post
Rust Gets a Garbage Collector
weeklyrust.substack.com·1d·
Discuss: Substack
🦀Rust Borrowing
Flag this post
Epistemic Deference to AI
arxiv.org·1d
🧮Theoretical Computer Science
Flag this post
Far from the Shallow: Brain-Predictive Reasoning Embedding through Residual Disentanglement
arxiv.org·22h
🔲Cellular Automata
Flag this post
Additive Models Explained: A Computational Complexity Approach
arxiv.org·1d
🧮Kolmogorov Complexity
Flag this post
Quantifying Explainable AI Reliability Through Causal Graph Reconstruction and HyperScore Validation
dev.to·7h·
Discuss: DEV
🔗Constraint Handling
Flag this post
Three Sins of Contextual Mismatch: Obscurity, Ambiguity, and Confabulation
medium.com·1d·
Discuss: Hacker News
🇸🇪Nordic Algorithms
Flag this post
Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)
arxiv.org·22h
💻Local LLMs
Flag this post
K-DAREK: Distance Aware Error for Kurkova Kolmogorov Networks
arxiv.org·22h
🧮Kolmogorov Complexity
Flag this post
RAG Pipelines Made Simple: Ballerina for AI-Powered Search
dev.to·4h·
Discuss: DEV
🤖Archive Automation
Flag this post
Interpretability Framework for LLMs in Undergraduate Calculus
arxiv.org·6d
🏗️Constructive Logic
Flag this post
VENI, VINDy, VICI: a generative reduced-order modeling framework with uncertainty quantification
arxiv.org·1d
Effect Handlers
Flag this post
Why I Changed My Mind About Code Comments
dev.to·1d·
Discuss: DEV
🛠Language Design
Flag this post
The Trojan Example: Jailbreaking LLMs through Template Filling and Unsafety Reasoning
arxiv.org·1d
🌐NetworkProtocols
Flag this post
Automated Validation of Distributed Systems Through Hyper-Scoring and Continuous Code Synthesis
dev.to·7h·
Discuss: DEV
🔍Concolic Testing
Flag this post