Interview: “Previous examination formats will be rendered useless by using AI”
heise.de·11h
📐Proof Assistants
My AI Workflow for Understanding Any Codebase
steipete.me·1d
⚡Proof Automation
Prompts vs. Context
dbreunig.com·17h
⚡Proof Automation
AST, Bytecode and the In Between: An Exploration of Interpreter Design Tradeoffs
2025.ecoop.org·17h·
Discuss: Hacker News
🔤DSLs
The Interactive Handbook on Data Structures and Algorithms
cartesian.app·2d·
Discuss: Lobsters, Hacker News, Hacker News
🌳Trie Structures
Leveraging Large Language Models for Information Verification -- an Engineering Approach
arxiv.org·2d
📋Document Grammar
Biomed-Enriched: A Biomedical Dataset Enriched with LLMs for Pretraining and Extracting Rare and Hidden Content
arxiv.org·13h
🔍Information Retrieval
Polynomial-Time Approximation Schemes via Utility Alignment: Unit-Demand Pricing and More
arxiv.org·13h
🎯Performance Proofs
PATCH! {P}sychometrics-{A}ssis{T}ed Ben{CH}marking of Large Language Models against Human Populations: A Case Study of Proficiency in 8th Grade Mathematics
arxiv.org·1d
🧠Intelligence Compression
Multilingual Tokenization through the Lens of Indian Languages: Challenges and Insights
arxiv.org·2d
📝Text Parsing
From Dev Blog to AI Discovery – How to Rank Your Content in Generative Search
dev.to·7h·
Discuss: DEV
📊Feed Optimization
Bilinear MLPs enable weight-based mechanistic interpretability
arxiv.org·13h
📊Quantization
Building Scalable Web Applications with Advanced JavaScript Patterns
dev.to·21h·
Discuss: DEV
🛠Language Design
CBF-AFA: Chunk-Based Multi-SSL Fusion for Automatic Fluency Assessment
arxiv.org·13h
🎙️Whisper
15 Go Packages Worth Your Time
dev.to·5h·
Discuss: DEV
💧Liquid Types
Piloting Copilot, Codex, and StarCoder2: Hot Temperature, Cold Prompts, or Black Magic?
arxiv.org·2d
✨Effect Handlers
Conversational Intent-Driven GraphRAG: Enhancing Multi-Turn Dialogue Systems through Adaptive Dual-Retrieval of Flow Patterns and Context Semantics
arxiv.org·1d
🧮Prolog Parsing
SUTRA: Decoupling Concept & Language for Multilingual LLM Excellence
hackernoon.com·1d
💻Local LLMs
Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs
arxiv.org·1d
💻Local LLMs
OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling
arxiv.org·13h
🔲Cellular Automata