All Posts - DataSci Ocean

All Posts

2026

WikiSkill: A Skill Memory That Never Gets Rolled Back 09-02

LLM-as-a-Verifier: A Better Alternative to LLM-as-a-Judge 08-26

RAGU: The Paper That Accidentally Measured GraphRAG's Ceiling 08-22

SAG: Multi-Hop RAG via Query-Time SQL, Not Offline Graphs 08-19

SketchVLM: Letting a VLM Draw Its Own Reasoning 08-08

Persona-Aware D2S: One Paper, Four Audience-Tailored Slide Decks 07-29

Claude Code Concepts: Agentic Loop, Tools, Skills, and Permissions 07-24

Cerebras's Enterprise RAG: Narrow-Waist Design, Decoupled Retrieval 07-23

SkillOpt: Treating an Agent's Skill File as a Trainable Weight 07-22

Adaptive Chunking: A Smarter, Per-Document Way to Split Text for RAG 07-22

Dropout Explained: The Simple Secret to Preventing Neural Network Overfitting 07-20

Understanding Backpropagation: How Gradients Are Calculated 07-15

An Introduction to Stochastic Gradient Descent 07-09

Deep Learning Fundamentals: An Introduction to Gradient Descent 06-28

Deep Learning Fundamentals: The MNIST Dataset and the Cost Function 06-20

Machine Learning Basics: The Bias-Variance Tradeoff 06-16

An Improved Perceptron: Understanding the Sigmoid Neuron 06-09

Beyond Text-to-SQL: Implementing OpenAI’s 6-Layer Context Data Agent and the Hidden Challenges 04-25

AgentOpt: How to Optimize Client-Side LLM Agents and Cut API Costs by 67% 04-17

ERL: Teaching LLM Agents to Learn from a Single Attempt Without Fine-Tuning 04-10

1
2
3
6