👑 Coq Tactics

Dependent Types, Proof Development, Ltac Programming, Mathematical Verification

A new information-theory framework reveals when multi-agent AI systems truly work as a team
the-decoder.com·13h
🔲Cellular Automata
Why do CPUs have multiple cache levels?
fgiesen.wordpress.com·5h·
Discuss: Hacker News
⚡Cache Theory
A gentle introduction to Generative AI: Historical perspective
medium.com·21h·
Discuss: Hacker News
🧠Learned Codecs
Why Haskell is the perfect fit for renewable energy tech
mrcjkb.dev·3d·
Discuss: Hacker News
🧬Functional Programming
The Alien Artifact: DSPy and the Cargo Cult of LLM Optimization
data-monger.com·4h·
Discuss: Hacker News
🔍Vector Forensics
Refactoring: A way to write better Code
dev.to·20h·
Discuss: DEV
⚙️Operational Semantics
LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?
arxiv.org·1d
🔗Parser Combinators
Unraveling LCRE-Mediated Chromatin Loops: A Predictive Model for Gene Expression Fine-Tuning in Desert Genomes
dev.to·1d·
Discuss: DEV
📥Feed Aggregation
Understanding Latent Space: How Meaning Is Represented by AI
dev.to·4h·
Discuss: DEV
🧮Kolmogorov Complexity
Community: The 100% Open-Source AI Stack That Automates My Business, and Tricks for Troubleshooting It
dev.to·3d·
Discuss: DEV
🏠Homelab Orchestration
ProofOfThought: LLM-based reasoning using Z3 theorem proving
dev.to·6d·
Discuss: DEV
⚡SMT Integration
AsyncSpade: Efficient Test-Time Scaling with Asynchronous Sparse Decoding
arxiv.org·1d
⚙️Compression Benchmarking
A small number of samples can poison LLMs of any size
dev.to·1d·
Discuss: DEV
💻Local LLMs
Krish Naik: Complete RAG Crash Course With Langchain In 2 Hours
dev.to·16h·
Discuss: DEV
📊Multi-vector RAG
A Manifesto for the Programming Desperado
github.com·1d·
Discuss: Hacker News
💻Programming languages
Is GRPO Broken?
neelsomaniblog.com·21h·
Discuss: Hacker News
🧮Kolmogorov Bounds
Prompt Injection 2.0: The New Frontier of AI Attacks
dev.to·2h·
Discuss: DEV
🎯Threat Hunting
LLM-Driven Rubric-Based Assessment of Algebraic Competence in Multi-Stage Block Coding Tasks with Design and Field Evaluation
arxiv.org·2d
💻Programming languages
h1: Bootstrapping LLMs to Reason over Longer Horizons via Reinforcement Learning
arxiv.org·2d·
Discuss: Hacker News
✓Automated Theorem Proving
TRIM: Token-wise Attention-Derived Saliency for Data-Efficient Instruction Tuning
arxiv.org·2d
🔨Compilers