Leetcode System DesignLearn how to design a scalable LeetCode-like system from scratch.7 min read·adityatrivedi.hashnode.devMay 7
Mastering the Low-Level Design (LLD) of Queues: Push vs. Pull Mechanisms ExplainedMaster the Low-Level Design of message queues. Discover the core differences and trade-offs between push and pull mechanisms in system design.6 min read·adityatrivedi.hashnode.devMay 6
Advanced Prompt Engineering Guide: Fundamentals to MultimodalMaster prompt engineering with our deep dive into In-Context Learning, security hardening, prompt chains, and multimodal AI evaluation techniques.10 min read·adityatrivedi.hashnode.devMay 1
What is an LLM Wiki and Why are People Paying Attention to it ?LLM suck at deep research.They can look at couple websites and get you surface level answers and this is how Karpathy's system does PhD level research17 min read·adityatrivedi.hashnode.devApr 7
PageIndex: Vectorless Reasoning-Based RAG FrameworkNot all improvements come from adding complexity -- sometimes it's about removing it. PageIndex takes a different approach to RAG. Instead of relying on vector databases or artificial chunking, it builds a hierarchical tree structure from documents and uses reasoning-based tree search to locate most relevant sections. This mirrors how humans approach reading: navigating through sections and context rather than matching embeddings. As a result, the retrieval feels transparent, structured, and explainable. It moves RAG away from approximate semantic vibes and towards explicit reasoning about where information lives.4 min read·adityatrivedi.hashnode.devMar 10