Cards

Developer-Gathered, AI-Crafted, Human-Checked.

Allrag(9)agents(7)security(6)prompt engineering(4)mcp(3)ocr(2)document conversion(2)vibe coding(2)embedding(2)evaluation(2)fine tuning(2)in-context learning(2)patterns(1)vision language model(1)openai(1)vector database(1)hallucination(1)web3(1)memory(1)transformer(1)

Where to show Demos in Your Prompt: A Positional Bias of In-Context Learning

RAG+: Enhancing Retrieval-Augmented Generation with Application-Aware Reasoning

MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models

Learning without training: The implicit dynamics of in-context learning

Retrieval-Augmented Reasoning with Lean Language Models

MCP vs CLI: Benchmarking Tools for Coding Agents

The MCP Security Survival Guide: Best Practices, Pitfalls, and Real-World Lessons

Tree of Thoughts: Deliberate Problem Solving with Large Language Models

Memory Decoder: A Pretrained, Plug-and-Play Memory for Large Language Models

Building a web search engine from scratch in two months with 3 billion neural embeddings

How to Hack a Web3 Wallet (Legally): A Full-Stack Pentesting Guide

Lost in the Middle: How Language Models Use Long Contexts

AI’s Security Crisis: Why Your Assistant Might Betray You

Lessons From Red Teaming 100 Generative AI Products

The Illusion of Progress: Re-evaluating Hallucination Detection in LLMs

LEANN: A Low-Storage Vector Index

GPT-5 prompting guide

SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion

Docling: An Efficient Open-Source Toolkit for AI-driven Document Conversion

Design Patterns for Securing LLM Agents against Prompt Injections