Is GRPO Broken?
neelsomaniblog.com·22h·
Discuss: Hacker News
🧮Kolmogorov Bounds
Show HN: Rebuilt Bible search app to run 100% client-side with Transformers.js
biblos.app·1d·
Discuss: Hacker News
📜Binary Philology
Speed Matters: How We Achieve the Fastest Web Agent
browser-use.com·2d·
Discuss: Hacker News
🎬WebCodecs
Revisiting Karpathy's 'Unreasonable Effectiveness of Recurrent Neural Networks'
gilesthomas.com·23h·
Discuss: Hacker News
🎧Learned Audio
The Tech Startup’s Guide to First-Time Advertising (TL;DR: Go Niche!)
hackernoon.com·1d
🔍BitFunnel
OpenAI's inflated valuation, as I understand it
taloranderson.com·1d·
Discuss: Hacker News
💻Local LLMs
AI as both authors and reviewers of research papers
openreview.net·2d·
Discuss: Hacker News
🔲Cellular Automata
Immersive Historical Reconstruction Validation via Multi-Sensor VR Data Fusion & Causal Inference
dev.to·1h·
Discuss: DEV
🏺Computational Archaeology
FocusMed: A Large Language Model-based Framework for Enhancing Medical Question Summarization with Focus Identification
arxiv.org·4d
🔍Information Retrieval
Krish Naik: Complete RAG Crash Course With Langchain In 2 Hours
dev.to·1d·
Discuss: DEV
📊Multi-vector RAG
AsyncSpade: Efficient Test-Time Scaling with Asynchronous Sparse Decoding
arxiv.org·1d
⚙️Compression Benchmarking
Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management
arxiv.org·2d
💻Local LLMs
Code Green: How Big Data and AI are Engineering a Sustainable Planet
dev.to·14h·
Discuss: DEV
🌊Stream Processing
Building Self-Correcting Database Agents with Meta's Llama-4-Scout: From Natural Language to SQL Insights
dev.to·2d·
Discuss: DEV
🗄️Database Internals
Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards
arxiv.org·1d
🧮Theorem Proving
Beyond Outcome Reward: Decoupling Search and Answering Improves LLM Agents
arxiv.org·4d
⚡Proof Automation
On the Relationship Between the Choice of Representation and In-Context Learning
arxiv.org·1d
📊Learned Metrics
Peeking inside the Black-Box: Reinforcement Learning for Explainable and Accurate Relation Extraction
arxiv.org·3d
🔍Information Retrieval
ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping
arxiv.org·1d
🧮Kolmogorov Complexity
Sales pitch about why you should learn statistics
minireference.com·1d
🧠Intelligence Compression