📚 Proof Pedagogy

Teaching Formal Methods, Interactive Learning, Mathematical Education, Verification Training, Beginner Proofs

News for September 2025
ptreview.sublinear.info·4d
🧪Property-Based Testing
This Puzzle Shows Just How Far LLMs Have Progressed in a Little Over a Year
towardsdatascience.com·1d
📐Mathematical Art
From Crypto Mining to Folding@Home: Using GPU Power for Something Good
dev.to·53m·
Discuss: DEV
🖥️Terminal Renaissance
Use 'Think, Pair, Share' for Effective Group Studying
lifehacker.com·1d
🧠Personal Knowledge Base
Context Length Alone Hurts LLM Performance Despite Perfect Retrieval
arxiv.org·11h
🧮Kolmogorov Complexity
PsycholexTherapy: Simulating Reasoning in Psychotherapy with Small Language Models in Persian
arxiv.org·1d
💻Programming languages
Lightweight Prompt Engineering for Cognitive Alignment in Educational AI: A OneClickQuiz Case Study
arxiv.org·1d
🤖AI Curation
H1B-KV: Hybrid One-Bit Caches for Memory-Efficient Large Language Model Inference
arxiv.org·11h
💨Cache Optimization
Unlocking Uniqueness: Mastering the Unique Character Algorithm in Go
dev.to·2d·
Discuss: DEV
🌳Trie Structures
Structured Cognition for Behavioral Intelligence in Large Language Model Agents: Preliminary Study
arxiv.org·11h
🧠Intelligence Compression
Krish Naik: Complete RAG Crash Course With Langchain In 2 Hours
dev.to·11h·
Discuss: DEV
⏰Temporal Logic
LexiCon: a Benchmark for Planning under Temporal Constraints in Natural Language
arxiv.org·11h
🧮Kolmogorov Complexity
You Can Get a Lifetime Subscription to Qlango for Just $32 Right Now
lifehacker.com·15h
🌳Context free grammars
Python 3.14 Unleashed: Revolutionary Features That Will Transform Your Code (Part 1)
dev.to·11h·
Discuss: DEV
💧Liquid Types
Assessment Twins: A Protocol for AI-Vulnerable Summative Assessment
arxiv.org·2d
🔲Cellular Automata
94% of AI Developers Ignore This Theorem Prover. Here's Why That's Costing Millions.
dev.to·3d·
Discuss: DEV
⚙️Proof Engineering
Beyond Transformers: Can MLPs Unlock the Potential of In-Context Learning?
dev.to·19h·
Discuss: DEV
🌳Context free grammars
Thinking on the Fly: Test-Time Reasoning Enhancement via Latent Thought Policy Optimization
arxiv.org·1d
💻Local LLMs
Detecting Distillation Data from Reasoning Models
arxiv.org·1d
⚙️ABNF Mining
Increasing LLM response trustworthiness using voting ensembles
arxiv.org·1d
🔍Information Retrieval