AtCoder Finals Problem Statement
atcoder.jp·22h·
Discuss: Hacker News
🇯🇵Japanese Computing
10 Python Math & Statistical Analysis One-Liners
kdnuggets.com·1d
📐Interval Arithmetic
SFT Is Bad RL
justinchiu.netlify.app·20h·
Discuss: Hacker News
🧠Machine Learning
Unlock Gemini’s reasoning: A step-by-step guide to logprobs on Vertex AI
developers.googleblog.com·19h
⚡Proof Automation
Cheating? Or the acumen of modern programming? FOSS, "AI", and human conscience
gist.github.com·14h·
Discuss: Hacker News
🔗Concatenative Programming
State of the Art of Prompt Engineering • Mike Taylor • GOTO 2025
youtube.com·4h
🖥️Terminal Renaissance
Could you be wrong: Debiasing LLMs using a metacognitive prompt for improving human decision making
arxiv.org·2d
🔲Cellular Automata
Developing Visual Augmented Q&A System using Scalable Vision Embedding Retrieval & Late Interaction Re-ranker
arxiv.org·12h
🧮Vector Embeddings
A Neural Network Model of Complementary Learning Systems: Pattern Separation and Completion for Continual Learning
arxiv.org·1d
🧠Neural Compression
How I Got 100/100 From GPT-4, Gemini, Grok, and More—Using Just a .txt File
dev.to·15h·
Discuss: DEV
⚔️Lean Tactics
Fine-tuning Large Language Model for Automated Algorithm Design
arxiv.org·1d
🔨Compilers
CompassJudger-2: Towards Generalist Judge Model via Verifiable Rewards
arxiv.org·2d
📊Learned Metrics
MediaMind AI - Intelligent Content Discovery Platform with Algolia MCP Server
dev.to·1d·
Discuss: DEV
🧭Content Discovery
DCR: Quantifying Data Contamination in LLMs Evaluation
arxiv.org·1d
✨Effect Handlers
Beyond Single Models: Enhancing LLM Detection of Ambiguity in Requests through Debate
arxiv.org·12h
📝ABNF Parsing
From Alerts to Intelligence: A Novel LLM-Aided Framework for Host-based Intrusion Detection
arxiv.org·1d
🎯Threat Hunting
Show HN: Context Rot Technical Report – How Input Length Impacts LLM Performance
research.trychroma.com·2d·
Discuss: Lobsters, Hacker News
🔍Information Retrieval
Sparse Identification of Nonlinear Dynamics with Conformal Prediction
arxiv.org·12h
🧮Kolmogorov Bounds
Grok 4: Elon Musk's Bold Gambit to Create the "Smartest AI in the World"
dev.to·1d·
Discuss: DEV
🏴󠁧󠁢󠁳󠁣󠁴󠁿Scottish Computing
AirLLM: Diffusion Policy-based Adaptive LoRA for Remote Fine-Tuning of LLM over the Air
arxiv.org·1d
💻Local LLMs