<?xml version="1.0" encoding="utf-8"?>
<rss version="2.0">
    <channel>
        <title>Developer Tutorials and Technical Guides | Krunal Kanojiya</title>
        <link>https://krunalkanojiya.com</link>
        <description>Practical tutorials and in-depth guides on AI engineering, data engineering, programming, algorithms, developer tools, and software development.</description>
        <lastBuildDate>Tue, 21 Jul 2026 00:00:00 GMT</lastBuildDate>
        <docs>https://validator.w3.org/feed/docs/rss2.html</docs>
        <generator>https://github.com/jpmonette/feed</generator>
        <language>en</language>
        <image>
            <title>Developer Tutorials and Technical Guides | Krunal Kanojiya</title>
            <url>https://2.gravatar.com/avatar/3c272c2728062fb969898e2b28814bde928c08683763c5c98a27b9a360b0f1fb?size=512&amp;d=initials</url>
            <link>https://krunalkanojiya.com</link>
        </image>
        <copyright>All rights reserved 2026, Krunal Kanojiya</copyright>
        <item>
            <title><![CDATA[Insertion Sort Algorithm: Complete Guide with Rust and Go]]></title>
            <link>https://krunalkanojiya.com/blog/insertion-sort-algorithm</link>
            <guid>https://krunalkanojiya.com/blog/insertion-sort-algorithm</guid>
            <pubDate>Tue, 21 Jul 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Learn insertion sort with a complete dry run, correctness and complexity analysis, shifting and binary-search variants, and tested Rust and Go implementations]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Sorting Algorithms</category>
        </item>
        <item>
            <title><![CDATA[Are AI Detectors Accurate? The Numbers and the Reasons They Fail]]></title>
            <link>https://krunalkanojiya.com/blog/are-ai-detectors-accurate</link>
            <guid>https://krunalkanojiya.com/blog/are-ai-detectors-accurate</guid>
            <pubDate>Sat, 25 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[AI detectors promise to catch AI-written text. This research-backed guide breaks down real detection rates, false positive rates, the technical reasons detection fails, tool comparisons, and real cases where false accusations caused harm.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>AI Engineering &amp; Trends</category>
        </item>
        <item>
            <title><![CDATA[Data Lake vs Data Warehouse vs Databricks Lakehouse]]></title>
            <link>https://krunalkanojiya.com/blog/data-lake-vs-data-warehouse-vs-databricks-lakehouse</link>
            <guid>https://krunalkanojiya.com/blog/data-lake-vs-data-warehouse-vs-databricks-lakehouse</guid>
            <pubDate>Wed, 15 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[What is the actual difference between a data lake, a data warehouse, and the Databricks Lakehouse? This article breaks down all three with plain language and simple diagrams so you understand exactly where each fits and why the Lakehouse exists.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Data Engineering</category>
        </item>
        <item>
            <title><![CDATA[Recursive Insertion Sort: Complete Guide with Rust and Go]]></title>
            <link>https://krunalkanojiya.com/blog/recursive-insertion-sort-algorithm</link>
            <guid>https://krunalkanojiya.com/blog/recursive-insertion-sort-algorithm</guid>
            <pubDate>Fri, 24 Jul 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Learn recursive insertion sort through a complete dry run, induction proof, recurrence and stack analysis, and tested Rust and Go implementations.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Sorting Algorithms</category>
        </item>
        <item>
            <title><![CDATA[Recursive Bubble Sort: Complete Guide with Rust and Go]]></title>
            <link>https://krunalkanojiya.com/blog/recursive-bubble-sort-algorithm</link>
            <guid>https://krunalkanojiya.com/blog/recursive-bubble-sort-algorithm</guid>
            <pubDate>Fri, 24 Jul 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Learn recursive bubble sort with a complete dry run, recurrence and stack-space analysis, early termination, and tested implementations in Rust and Go.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Sorting Algorithms</category>
        </item>
        <item>
            <title><![CDATA[Quick Sort Algorithm: Complete Guide with Rust and Go]]></title>
            <link>https://krunalkanojiya.com/blog/quick-sort-algorithm</link>
            <guid>https://krunalkanojiya.com/blog/quick-sort-algorithm</guid>
            <pubDate>Fri, 24 Jul 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Learn quick sort with a three-way partition dry run, correctness and complexity analysis, pivot strategies, and tested Rust and Go implementations.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Sorting Algorithms</category>
        </item>
        <item>
            <title><![CDATA[Merge Sort Algorithm: Complete Guide with Rust and Go]]></title>
            <link>https://krunalkanojiya.com/blog/merge-sort-algorithm</link>
            <guid>https://krunalkanojiya.com/blog/merge-sort-algorithm</guid>
            <pubDate>Fri, 24 Jul 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Learn merge sort with a complete divide-and-merge walkthrough, recurrence and complexity analysis, stability rules, and tested Rust and Go implementations.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Sorting Algorithms</category>
        </item>
        <item>
            <title><![CDATA[Bubble Sort Algorithm: Complete Guide with Rust and Go]]></title>
            <link>https://krunalkanojiya.com/blog/bubble-sort-algorithm</link>
            <guid>https://krunalkanojiya.com/blog/bubble-sort-algorithm</guid>
            <pubDate>Tue, 21 Jul 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Learn bubble sort with a complete dry run, optimized early-exit algorithm, complexity and stability analysis, and tested implementations in Rust and Go.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Sorting Algorithms</category>
        </item>
        <item>
            <title><![CDATA[Selection Sort Algorithm: Step-by-Step Guide with Rust and Go]]></title>
            <link>https://krunalkanojiya.com/blog/selection-sort-algorithm</link>
            <guid>https://krunalkanojiya.com/blog/selection-sort-algorithm</guid>
            <pubDate>Tue, 21 Jul 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Learn how selection sort works with a complete dry run, pseudocode, complexity analysis, common mistakes, and tested implementations in Rust and Go.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Sorting Algorithms</category>
        </item>
        <item>
            <title><![CDATA[RAG Reranking Explained: Models, Metrics, and Production Trade-Offs]]></title>
            <link>https://krunalkanojiya.com/blog/rag-reranking-explained</link>
            <guid>https://krunalkanojiya.com/blog/rag-reranking-explained</guid>
            <pubDate>Sun, 19 Jul 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Learn how reranking improves RAG retrieval precision, when to use cross-encoders and other rerankers, how to tune candidate depth, and how to evaluate the result.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>RAG</category>
        </item>
        <item>
            <title><![CDATA[RAG Architecture Explained: How Production Pipelines Actually Work (2026)]]></title>
            <link>https://krunalkanojiya.com/blog/rag-architecture-explained</link>
            <guid>https://krunalkanojiya.com/blog/rag-architecture-explained</guid>
            <pubDate>Mon, 04 May 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Naive RAG fails 40% of the time at retrieval. This guide breaks down every layer of a production RAG architecture - chunking strategies, embedding selection, hybrid search, reranking, query transformation, agentic RAG, and evaluation with RAGAS - with working Python code for each component.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>RAG</category>
        </item>
        <item>
            <title><![CDATA[Hybrid Search for RAG Explained: BM25, Vector Search, and RRF]]></title>
            <link>https://krunalkanojiya.com/blog/hybrid-search-for-rag</link>
            <guid>https://krunalkanojiya.com/blog/hybrid-search-for-rag</guid>
            <pubDate>Sat, 18 Jul 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Learn how hybrid search improves RAG by combining BM25 keyword retrieval with dense vector search, fusing results with RRF, and evaluating the pipeline on real queries.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>RAG</category>
        </item>
        <item>
            <title><![CDATA[Vector Search vs Semantic Search: What Is the Difference?]]></title>
            <link>https://krunalkanojiya.com/blog/vector-search-vs-semantic-search</link>
            <guid>https://krunalkanojiya.com/blog/vector-search-vs-semantic-search</guid>
            <pubDate>Thu, 16 Jul 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Vector search and semantic search are closely related, but they are not exactly the same. Learn the technical difference, how each works, when the terms overlap, and how they fit into keyword search, hybrid search, and RAG.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Vector Search &amp; Databases</category>
        </item>
        <item>
            <title><![CDATA[How to Choose Chunk Size for RAG: A Practical Guide]]></title>
            <link>https://krunalkanojiya.com/blog/how-to-choose-chunk-size-for-rag</link>
            <guid>https://krunalkanojiya.com/blog/how-to-choose-chunk-size-for-rag</guid>
            <pubDate>Thu, 16 Jul 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Learn how to choose chunk size and overlap for RAG using practical starting ranges, document-specific recommendations, retrieval metrics, and a repeatable evaluation workflow.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>RAG</category>
        </item>
        <item>
            <title><![CDATA[What Is Vector Search? A Beginner-Friendly Guide]]></title>
            <link>https://krunalkanojiya.com/blog/what-is-vector-search</link>
            <guid>https://krunalkanojiya.com/blog/what-is-vector-search</guid>
            <pubDate>Tue, 14 Jul 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[A beginner-friendly explanation of vector search: how AI turns text into embeddings, how similarity search finds meaning instead of keywords, where vector databases fit, and why vector search powers semantic search and RAG applications.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Vector Search &amp; Databases</category>
        </item>
        <item>
            <title><![CDATA[Pinecone vs Qdrant: Which Vector Database Should You Use in 2026?]]></title>
            <link>https://krunalkanojiya.com/blog/pinecone-vs-qdrant</link>
            <guid>https://krunalkanojiya.com/blog/pinecone-vs-qdrant</guid>
            <pubDate>Thu, 28 May 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Pinecone and Qdrant are the two most popular vector databases for production RAG applications in 2026. This is a side-by-side comparison of their architecture, performance, filtering, hybrid search, cost, and developer experience so you can pick the right one for your stack.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Vector Search &amp; Databases</category>
        </item>
        <item>
            <title><![CDATA[IVF Index Explained for Vector Search]]></title>
            <link>https://krunalkanojiya.com/blog/ivf-index-explained</link>
            <guid>https://krunalkanojiya.com/blog/ivf-index-explained</guid>
            <pubDate>Mon, 27 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[A research-backed technical explanation of the Inverted File Index (IVF) for vector similarity search. Learn how k-means training partitions the vector space, how the two-stage coarse-to-fine search works, how nlist and nprobe control the recall-latency tradeoff, how IVF-PQ extends IVF for billion-scale deployments, and when to choose IVF over HNSW.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Vector Search &amp; Databases</category>
        </item>
        <item>
            <title><![CDATA[Token and Positional Embeddings: How Transformers Represent Words (RoPE Explained)]]></title>
            <link>https://krunalkanojiya.com/blog/embeddings-representation-learning</link>
            <guid>https://krunalkanojiya.com/blog/embeddings-representation-learning</guid>
            <pubDate>Thu, 09 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[How a transformer represents tokens inside the model: the token embedding lookup table, positional embeddings, the path from sinusoidal encoding to RoPE and ALiBi, and why vector-space geometry matters for everything downstream.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>LLMs &amp; Deep Learning</category>
        </item>
        <item>
            <title><![CDATA[Databricks vs Snowflake in 2026: The Honest Technical Comparison for Data Teams]]></title>
            <link>https://krunalkanojiya.com/blog/databricks-vs-snowflake</link>
            <guid>https://krunalkanojiya.com/blog/databricks-vs-snowflake</guid>
            <pubDate>Thu, 30 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Databricks or Snowflake? This research-backed comparison covers architecture, performance benchmarks, real pricing numbers, AI capabilities, governance, and a clear decision framework for data engineers, analysts, and engineering leaders in 2026.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Data Engineering</category>
        </item>
        <item>
            <title><![CDATA[What Is a Vector Database? The Complete Beginner Guide (With Examples)]]></title>
            <link>https://krunalkanojiya.com/blog/vector-database</link>
            <guid>https://krunalkanojiya.com/blog/vector-database</guid>
            <pubDate>Thu, 23 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[A complete beginner guide to vector databases. Learn how they store high-dimensional embeddings, how similarity search works, how they differ from SQL databases, and why every serious AI application needs one.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Vector Search &amp; Databases</category>
        </item>
        <item>
            <title><![CDATA[Elasticsearch Vector Search vs Vector Databases: Which Should You Use?]]></title>
            <link>https://krunalkanojiya.com/blog/vector-database-vs-elasticsearch</link>
            <guid>https://krunalkanojiya.com/blog/vector-database-vs-elasticsearch</guid>
            <pubDate>Fri, 24 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[A research-backed comparison of dedicated vector databases and Elasticsearch for AI search workloads. Learn how their architectures differ, what the benchmarks say about latency and indexing speed, where each system wins, and a practical decision framework for your stack in 2026.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Vector Search &amp; Databases</category>
        </item>
        <item>
            <title><![CDATA[Lakebase LTAP Explained: How Databricks Is Merging OLTP and OLAP in 2026]]></title>
            <link>https://krunalkanojiya.com/blog/lakebase-ltap-explained</link>
            <guid>https://krunalkanojiya.com/blog/lakebase-ltap-explained</guid>
            <pubDate>Sat, 11 Jul 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Databricks announced LTAP in June 2026, a new architecture that runs transactional and analytical workloads on a single copy of data. This is a technical breakdown of how Lakebase and LTAP actually work, what problem they solve, and where the skepticism from competitors comes from.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Data Engineering</category>
        </item>
        <item>
            <title><![CDATA[How to Build a RAG Application with LangChain and Pinecone (Step-by-Step)]]></title>
            <link>https://krunalkanojiya.com/blog/build-rag-application-langchain-pinecone</link>
            <guid>https://krunalkanojiya.com/blog/build-rag-application-langchain-pinecone</guid>
            <pubDate>Wed, 01 Jul 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[A complete, working tutorial for building a Retrieval-Augmented Generation application using LangChain and Pinecone. Covers document loading, chunking, embeddings, indexing, retrieval, and generation with full Python code.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>AI Engineering &amp; Trends</category>
        </item>
        <item>
            <title><![CDATA[Pinecone vs Weaviate vs Milvus vs Qdrant: Best Vector Database in 2026?]]></title>
            <link>https://krunalkanojiya.com/blog/pinecone-vs-weaviate-vs-milvus-vs-qdrant</link>
            <guid>https://krunalkanojiya.com/blog/pinecone-vs-weaviate-vs-milvus-vs-qdrant</guid>
            <pubDate>Sat, 27 Jun 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Pinecone, Weaviate, Milvus, and Qdrant are the four most widely used vector databases for production AI applications in 2026. This is a side-by-side comparison of their architecture, performance, filtering, hybrid search, cost, and developer experience so you can pick the right one for your stack.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Vector Search &amp; Databases</category>
        </item>
        <item>
            <title><![CDATA[Qdrant vs Weaviate: Which Vector Database Should You Use in 2026?]]></title>
            <link>https://krunalkanojiya.com/blog/qdrant-vs-weaviate</link>
            <guid>https://krunalkanojiya.com/blog/qdrant-vs-weaviate</guid>
            <pubDate>Sun, 07 Jun 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Qdrant and Weaviate are both strong open-source vector databases, but they are built for different teams. This side-by-side comparison covers architecture, API style, filtering, hybrid search, multi-tenancy, cost, and a clear recommendation for each use case.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Vector Search &amp; Databases</category>
        </item>
        <item>
            <title><![CDATA[Qdrant Tutorial: Getting Started with Vector Search in Python (2026)]]></title>
            <link>https://krunalkanojiya.com/blog/qdrant-getting-started-guide</link>
            <guid>https://krunalkanojiya.com/blog/qdrant-getting-started-guide</guid>
            <pubDate>Sun, 07 Jun 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[A complete Qdrant tutorial for 2026. Covers Docker setup, creating collections, inserting vectors with Python, similarity search, metadata filtering, hybrid search, and payload indexing. Includes working code for every step.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Vector Search &amp; Databases</category>
        </item>
        <item>
            <title><![CDATA[pgvector vs Pinecone: Which One Should You Use in 2026?]]></title>
            <link>https://krunalkanojiya.com/blog/pgvector-vs-pinecone</link>
            <guid>https://krunalkanojiya.com/blog/pgvector-vs-pinecone</guid>
            <pubDate>Sun, 07 Jun 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[pgvector or Pinecone? This honest comparison covers setup, performance, cost, filtering, hybrid search, and the real question most teams miss: when does your Postgres setup stop being enough?]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Vector Search &amp; Databases</category>
        </item>
        <item>
            <title><![CDATA[Why RAG Fails: Every Failure Mode and How to Fix Each One (2026)]]></title>
            <link>https://krunalkanojiya.com/blog/why-rag-fails</link>
            <guid>https://krunalkanojiya.com/blog/why-rag-fails</guid>
            <pubDate>Thu, 07 May 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[RAG fails at retrieval 73% of the time, not generation. This guide covers every production failure mode - chunking artifacts, vocabulary mismatch, lost in the middle, missing reranking, stale indexes, and no evaluation layer - with specific fixes for each, backed by 2025 and 2026 production data.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>RAG</category>
        </item>
        <item>
            <title><![CDATA[What Is Semantic Search? How It Works Step by Step]]></title>
            <link>https://krunalkanojiya.com/blog/what-is-semantic-search</link>
            <guid>https://krunalkanojiya.com/blog/what-is-semantic-search</guid>
            <pubDate>Thu, 23 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[A research-backed, step-by-step guide to semantic search. Learn how it differs from keyword search, how the full pipeline works from chunking to reranking, what makes it fail, and how to build a working semantic search system with Python code examples.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Vector Search &amp; Databases</category>
        </item>
        <item>
            <title><![CDATA[What Is RAG in AI? A Simple Explanation (With Examples)]]></title>
            <link>https://krunalkanojiya.com/blog/what-is-rag-in-ai</link>
            <guid>https://krunalkanojiya.com/blog/what-is-rag-in-ai</guid>
            <pubDate>Tue, 05 May 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[RAG stands for Retrieval-Augmented Generation. It solves the biggest problem with LLMs - they only know what they were trained on. This guide explains how RAG works, why it exists, and where it is used in production AI systems in 2026.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>RAG</category>
        </item>
        <item>
            <title><![CDATA[What Is Databricks? A Simple Beginner-Friendly Explanation]]></title>
            <link>https://krunalkanojiya.com/blog/what-is-databricks</link>
            <guid>https://krunalkanojiya.com/blog/what-is-databricks</guid>
            <pubDate>Sun, 12 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[New to Databricks and not sure where to start? This beginner guide explains what Databricks actually is, what problems it solves, and why data teams in 2026 keep reaching for it, no jargon required.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Data Engineering</category>
        </item>
        <item>
            <title><![CDATA[What Are Embeddings? How AI Converts Text Into Numbers]]></title>
            <link>https://krunalkanojiya.com/blog/what-are-embeddings</link>
            <guid>https://krunalkanojiya.com/blog/what-are-embeddings</guid>
            <pubDate>Thu, 23 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[A research-backed explanation of what embeddings are in machine learning. Learn how AI models convert text, images, and audio into numerical vectors, how transformer-based embedding models work, and how embeddings power semantic search, RAG pipelines, and vector databases.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>ML Foundations</category>
        </item>
        <item>
            <title><![CDATA[Vector Query Lifecycle Explained Step by Step]]></title>
            <link>https://krunalkanojiya.com/blog/vector-query-lifecycle-explained</link>
            <guid>https://krunalkanojiya.com/blog/vector-query-lifecycle-explained</guid>
            <pubDate>Wed, 29 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[A research-backed, step-by-step walkthrough of everything that happens inside a vector database from the moment a query request arrives to the moment results are returned. Covers API parsing, filter strategy selection, ANN index traversal, multi-segment merge, distributed shard coordination, payload fetch, scoring, and response serialization.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Vector Search &amp; Databases</category>
        </item>
        <item>
            <title><![CDATA[Transformer Architecture and Attention: Why Every Modern LLM Is Built This Way]]></title>
            <link>https://krunalkanojiya.com/blog/transformer-architecture-attention</link>
            <guid>https://krunalkanojiya.com/blog/transformer-architecture-attention</guid>
            <pubDate>Wed, 15 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[The transformer solved three problems that broke RNNs: sequential computation, vanishing gradients over long distances, and fixed-size bottlenecks. This article walks through self-attention from dot products to multi-head, the full transformer block, and how modern optimizations like FlashAttention and GQA work.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>LLMs &amp; Deep Learning</category>
        </item>
        <item>
            <title><![CDATA[Prompting, RAG, and In-Context Learning: Using LLMs in Real Products]]></title>
            <link>https://krunalkanojiya.com/blog/prompting-rag-in-context-learning</link>
            <guid>https://krunalkanojiya.com/blog/prompting-rag-in-context-learning</guid>
            <pubDate>Mon, 20 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Knowing how to build a transformer is one thing. Knowing how to use one in production is another. This article covers prompt engineering, few-shot learning, chain-of-thought, retrieval-augmented generation, and why the model's behavior shifts so dramatically based on how you frame your request.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>RAG</category>
        </item>
        <item>
            <title><![CDATA[I Built a Tiny GPT Model From Scratch: Here's Exactly How It Works]]></title>
            <link>https://krunalkanojiya.com/blog/i-built-a-tiny-gpt-model-from-scratch</link>
            <guid>https://krunalkanojiya.com/blog/i-built-a-tiny-gpt-model-from-scratch</guid>
            <pubDate>Tue, 31 Mar 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[How GPT really works, explained by building a 10M-parameter model from scratch in PyTorch. Covers tokenization, attention, transformer blocks, training, and text generation - all in ~300 lines of Python.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>LLMs &amp; Deep Learning</category>
        </item>
        <item>
            <title><![CDATA[How Vector Databases Work Internally: Indexing, Search and Storage Explained]]></title>
            <link>https://krunalkanojiya.com/blog/how-vector-databases-work</link>
            <guid>https://krunalkanojiya.com/blog/how-vector-databases-work</guid>
            <pubDate>Sat, 25 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[A technical deep dive into how vector databases work under the hood. Learn how the ingestion pipeline, storage layer, ANN index structures, similarity metrics, query lifecycle, metadata filtering, and distributed architecture fit together inside production vector database systems.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Vector Search &amp; Databases</category>
        </item>
        <item>
            <title><![CDATA[How Similarity Search Works in Vector Databases]]></title>
            <link>https://krunalkanojiya.com/blog/how-similarity-search-works</link>
            <guid>https://krunalkanojiya.com/blog/how-similarity-search-works</guid>
            <pubDate>Sun, 26 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[A research-backed, step-by-step explanation of how similarity search works inside a vector database. Covers distance computation, candidate retrieval from ANN indexes, score normalization, metadata filtering, post-processing, and reranking with working Python code examples.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Vector Search &amp; Databases</category>
        </item>
        <item>
            <title><![CDATA[Exploration Hacking: The RL Failure Mode That ML Engineers Need to Understand Now]]></title>
            <link>https://krunalkanojiya.com/blog/exploration-hacking-llm-rl-resistance</link>
            <guid>https://krunalkanojiya.com/blog/exploration-hacking-llm-rl-resistance</guid>
            <pubDate>Tue, 05 May 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[A new paper from MATS, Anthropic, Google DeepMind, and UC San Diego shows that AI models can deliberately underperform during their own RL training to prevent capability updates. Here is what exploration hacking is, how it works, what the experiments found, and what mitigations actually help.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>LLMs &amp; Deep Learning</category>
        </item>
        <item>
            <title><![CDATA[Exact vs Approximate Nearest Neighbor (ANN) Explained]]></title>
            <link>https://krunalkanojiya.com/blog/exact-vs-approximate-nearest-neighbor</link>
            <guid>https://krunalkanojiya.com/blog/exact-vs-approximate-nearest-neighbor</guid>
            <pubDate>Sun, 26 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[A research-backed, technically precise explanation of exact nearest neighbor search versus approximate nearest neighbor (ANN) algorithms. Learn why exact search fails at scale, how ANN achieves massive speedups with bounded accuracy loss, how recall is measured, and how to tune ANN parameters for your production workload.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Vector Search &amp; Databases</category>
        </item>
        <item>
            <title><![CDATA[Evaluation, Inference, and Deployment: Shipping an LLM Product That Actually Works]]></title>
            <link>https://krunalkanojiya.com/blog/evaluation-inference-deployment</link>
            <guid>https://krunalkanojiya.com/blog/evaluation-inference-deployment</guid>
            <pubDate>Tue, 21 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Building a model is one thing. Knowing whether it works, making it fast enough to serve, and keeping it working in production is another. This final article covers benchmarks, quantization, KV cache, latency, and what breaks when you move from research to real users.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>LLMs &amp; Deep Learning</category>
        </item>
        <item>
            <title><![CDATA[Cosine Similarity vs Euclidean Distance Explained]]></title>
            <link>https://krunalkanojiya.com/blog/cosine-similarity-vs-euclidean-distance</link>
            <guid>https://krunalkanojiya.com/blog/cosine-similarity-vs-euclidean-distance</guid>
            <pubDate>Sun, 26 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[A research-backed, mathematically precise explanation of cosine similarity vs Euclidean distance for vector search. Learn the geometry behind each metric, when each is the right choice, how dot product relates to both, and what happens when you pick the wrong metric for your embedding model.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Vector Search &amp; Databases</category>
        </item>
        <item>
            <title><![CDATA[Product Quantization Explained Simply]]></title>
            <link>https://krunalkanojiya.com/blog/product-quantization-explained</link>
            <guid>https://krunalkanojiya.com/blog/product-quantization-explained</guid>
            <pubDate>Tue, 28 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[A research-backed explanation of Product Quantization (PQ) for vector compression. Learn how subspace decomposition reduces vector storage by 32 to 64 times, how codebooks are trained, how asymmetric distance computation preserves search speed, how to tune M and nbits, and when to use PQ with IVF or HNSW.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Vector Search &amp; Databases</category>
        </item>
        <item>
            <title><![CDATA[HNSW Algorithm Explained With Diagrams]]></title>
            <link>https://krunalkanojiya.com/blog/hnsw-algorithm-explained</link>
            <guid>https://krunalkanojiya.com/blog/hnsw-algorithm-explained</guid>
            <pubDate>Mon, 27 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[A research-backed, diagram-rich explanation of the HNSW (Hierarchical Navigable Small World) algorithm. Learn how the layered graph is built, how query traversal works layer by layer, how the three key parameters M, ef_construction, and ef_search control the recall-latency tradeoff, and how to tune HNSW for production vector search workloads.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Vector Search &amp; Databases</category>
        </item>
        <item>
            <title><![CDATA[Dense vs Sparse Vectors Explained With Examples]]></title>
            <link>https://krunalkanojiya.com/blog/dense-vs-sparse-vectors</link>
            <guid>https://krunalkanojiya.com/blog/dense-vs-sparse-vectors</guid>
            <pubDate>Thu, 23 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[A research-backed guide to dense and sparse vectors in machine learning. Learn how each representation works, when to use BM25 versus embeddings, how SPLADE bridges both worlds, and why hybrid search combining dense and sparse retrieval consistently outperforms either method alone.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Vector Search &amp; Databases</category>
        </item>
        <item>
            <title><![CDATA[pgvector: The Complete Guide to Vector Search in PostgreSQL (2026)]]></title>
            <link>https://krunalkanojiya.com/blog/pgvector-postgresql-guide</link>
            <guid>https://krunalkanojiya.com/blog/pgvector-postgresql-guide</guid>
            <pubDate>Fri, 29 May 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[pgvector adds vector similarity search directly to PostgreSQL. This guide covers installation, creating vector columns, HNSW and IVFFlat indexes, cosine and L2 distance queries, filtering, Python integration, performance tuning, and when to migrate to a dedicated vector database.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Vector Search &amp; Databases</category>
        </item>
        <item>
            <title><![CDATA[How to Choose a Vector Database in 2026: The Decision Guide]]></title>
            <link>https://krunalkanojiya.com/blog/how-to-choose-a-vector-database</link>
            <guid>https://krunalkanojiya.com/blog/how-to-choose-a-vector-database</guid>
            <pubDate>Wed, 27 May 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Every vector database comparison ends with 'it depends on your use case.' This one does not. A practical framework that maps your scale, budget, and infrastructure to a clear recommendation across Pinecone, Qdrant, Weaviate, Milvus, pgvector, and Chroma.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Vector Search &amp; Databases</category>
        </item>
        <item>
            <title><![CDATA[Why Your Vector Search Returns 'Close But Not Quite Right' Results]]></title>
            <link>https://krunalkanojiya.com/blog/dual-encoders-vs-cross-encoders-search-pipeline</link>
            <guid>https://krunalkanojiya.com/blog/dual-encoders-vs-cross-encoders-search-pipeline</guid>
            <pubDate>Tue, 26 May 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Most RAG pipelines stop at the dual encoder. That is the mistake. This guide explains why modern search systems chain dual encoders and cross-encoders together, how each one works, and how to implement the two-stage pipeline in Python.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>RAG</category>
        </item>
        <item>
            <title><![CDATA[RAG Evaluation as an Engineering Discipline: Build the Pipeline From Zero]]></title>
            <link>https://krunalkanojiya.com/blog/rag-evaluation-engineering</link>
            <guid>https://krunalkanojiya.com/blog/rag-evaluation-engineering</guid>
            <pubDate>Fri, 15 May 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[57% of organizations have RAG agents in production. 32% cite quality as the top barrier. Systematic evaluation reduces post-deployment failures by 50 to 70%, but most teams still treat it as a one-time check. This is the practitioner's guide: what metrics matter, how to build a CI/CD quality gate, and how to wire production failures back into your test suite without buying another SaaS tool.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>RAG</category>
        </item>
        <item>
            <title><![CDATA[RAG vs LangChain: What They Are, How They Relate, and Which One You Actually Need]]></title>
            <link>https://krunalkanojiya.com/blog/rag-vs-langchain</link>
            <guid>https://krunalkanojiya.com/blog/rag-vs-langchain</guid>
            <pubDate>Sat, 09 May 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[RAG is a retrieval technique. LangChain is an orchestration framework. Comparing them directly is a category error - but the question developers are really asking is whether LangChain is necessary to build a RAG system. This guide answers that with benchmarks, real code, and a decision framework grounded in 2026 production data.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>RAG</category>
        </item>
        <item>
            <title><![CDATA[RAG vs Traditional Search: What Changed, What Did Not, and Why BM25 Is Not Dead]]></title>
            <link>https://krunalkanojiya.com/blog/rag-vs-traditional-search</link>
            <guid>https://krunalkanojiya.com/blog/rag-vs-traditional-search</guid>
            <pubDate>Fri, 08 May 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Traditional search returns documents. RAG returns answers. That gap sounds simple but it changes everything about how you build, evaluate, and maintain an information retrieval system. This guide breaks down how keyword search, semantic search, and RAG differ, where each wins, and why the best production systems in 2026 combine all three.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>RAG</category>
        </item>
        <item>
            <title><![CDATA[How Embeddings Work in RAG: The Complete Guide (2026)]]></title>
            <link>https://krunalkanojiya.com/blog/how-embeddings-work-in-rag</link>
            <guid>https://krunalkanojiya.com/blog/how-embeddings-work-in-rag</guid>
            <pubDate>Fri, 08 May 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Embeddings are the invisible foundation of every RAG retrieval pipeline. This guide explains what embeddings are, how transformers produce them, why cosine similarity works, the difference between bi-encoders and cross-encoders, how to choose an embedding model in 2026, and where retrieval quality silently breaks down.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>RAG</category>
        </item>
        <item>
            <title><![CDATA[Vector Database in RAG: How It Works, Which One to Pick (2026 Guide)]]></title>
            <link>https://krunalkanojiya.com/blog/vector-database-in-rag</link>
            <guid>https://krunalkanojiya.com/blog/vector-database-in-rag</guid>
            <pubDate>Wed, 06 May 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[The vector database is the retrieval engine behind every RAG system. This guide covers HNSW indexing, how cosine similarity works, pgvector vs purpose-built databases, real cost numbers at scale, and a decision framework for picking between Pinecone, Qdrant, Weaviate, Milvus, and Chroma in 2026.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Vector Search &amp; Databases</category>
        </item>
        <item>
            <title><![CDATA[RAG vs Fine-Tuning: When to Use Each (2026 Decision Guide)]]></title>
            <link>https://krunalkanojiya.com/blog/rag-vs-fine-tuning</link>
            <guid>https://krunalkanojiya.com/blog/rag-vs-fine-tuning</guid>
            <pubDate>Mon, 04 May 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[RAG and fine-tuning solve different problems. RAG changes what the model knows at query time. Fine-tuning changes how the model behaves permanently. This guide breaks down the real cost numbers, failure modes, and a practical decision framework for 2026.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>RAG</category>
        </item>
        <item>
            <title><![CDATA[Mosaic AI Agent Framework: The Complete Guide for Building Production AI Agents on Databricks in 2026]]></title>
            <link>https://krunalkanojiya.com/blog/mosaic-ai-agent-framework</link>
            <guid>https://krunalkanojiya.com/blog/mosaic-ai-agent-framework</guid>
            <pubDate>Sun, 03 May 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Mosaic AI Agent Framework is Databricks' built-in platform for building, evaluating, and deploying enterprise AI agents. This research-backed guide covers every component from Vector Search and MLflow tracing to Agent Bricks, Unity Catalog governance, and MCP integration, with real enterprise examples.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>AI Engineering &amp; Trends</category>
        </item>
        <item>
            <title><![CDATA[Physical AI for ML Engineers: What's Actually Different About Training Models That Control Robots]]></title>
            <link>https://krunalkanojiya.com/blog/physical-ai-for-ml-engineers</link>
            <guid>https://krunalkanojiya.com/blog/physical-ai-for-ml-engineers</guid>
            <pubDate>Sat, 02 May 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[If you train language or vision models and want to move into physical AI, this is the transition guide nobody wrote. What changes about your data pipeline, your training loop, your evaluation setup, and your mental model when your model's outputs move motors instead of tokens.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>AI Engineering &amp; Trends</category>
        </item>
        <item>
            <title><![CDATA[Databricks Lakehouse Fundamentals Guide for Beginners 2026]]></title>
            <link>https://krunalkanojiya.com/blog/databricks-lakehouse-fundamentals-guide</link>
            <guid>https://krunalkanojiya.com/blog/databricks-lakehouse-fundamentals-guide</guid>
            <pubDate>Thu, 30 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[A complete reference guide to how the Databricks Lakehouse platform is actually structured in 2026. Covers the workspace, Unity Catalog hierarchy, compute options, Medallion architecture, Lakeflow pipelines, and where to go next.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Data Engineering</category>
        </item>
        <item>
            <title><![CDATA[What Is Vector Indexing and Why It Matters]]></title>
            <link>https://krunalkanojiya.com/blog/what-is-vector-indexing</link>
            <guid>https://krunalkanojiya.com/blog/what-is-vector-indexing</guid>
            <pubDate>Wed, 29 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[A research-backed guide to vector indexing: what it is, why it exists, how the three-way tradeoff between recall, latency, and memory shapes every index decision, how to select the right index type for your workload, how to measure index quality, and the operational factors that affect index performance in production.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Vector Search &amp; Databases</category>
        </item>
        <item>
            <title><![CDATA[UCP vs ACP vs MCP: Which Shopify Protocol Actually Matters for Your Store in 2026]]></title>
            <link>https://krunalkanojiya.com/blog/ucp-vs-acp-vs-mcp-shopify-protocols</link>
            <guid>https://krunalkanojiya.com/blog/ucp-vs-acp-vs-mcp-shopify-protocols</guid>
            <pubDate>Wed, 29 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Three protocols are competing to define how AI agents shop for your customers. This plain-English guide breaks down UCP, ACP, and MCP for Shopify developers and agencies - what each one does, where they overlap, and what to actually build first.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>AI Engineering &amp; Trends</category>
        </item>
        <item>
            <title><![CDATA[Why Traditional Indexes Fail for Vector Search]]></title>
            <link>https://krunalkanojiya.com/blog/why-traditional-indexes-fail-for-vector-search</link>
            <guid>https://krunalkanojiya.com/blog/why-traditional-indexes-fail-for-vector-search</guid>
            <pubDate>Fri, 24 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[A research-backed deep dive into why B-tree and hash indexes cannot handle high-dimensional vector search. Learn about the curse of dimensionality, why traditional structures break down above 10 to 15 dimensions, and how HNSW and IVF were designed from first principles to solve the problem.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Vector Search &amp; Databases</category>
        </item>
        <item>
            <title><![CDATA[Vector Database vs Traditional Database: Key Differences]]></title>
            <link>https://krunalkanojiya.com/blog/vector-database-vs-traditional-database</link>
            <guid>https://krunalkanojiya.com/blog/vector-database-vs-traditional-database</guid>
            <pubDate>Fri, 24 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[A research-backed comparison of vector databases and traditional relational databases. Learn how their data models, index structures, query languages, and scalability patterns differ, when to use each, and how pgvector bridges both worlds for teams already running PostgreSQL.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>Vector Search &amp; Databases</category>
        </item>
        <item>
            <title><![CDATA[Latent Space Explained: The Hidden Structure of AI Models]]></title>
            <link>https://krunalkanojiya.com/blog/latent-space-explained</link>
            <guid>https://krunalkanojiya.com/blog/latent-space-explained</guid>
            <pubDate>Fri, 24 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[A research-backed explanation of latent space in AI and machine learning. Learn what latent space is, how models learn it, why its geometry encodes meaning, how vector arithmetic works inside it, and why understanding it makes you a better AI engineer.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>ML Foundations</category>
        </item>
        <item>
            <title><![CDATA[What Is a Vector in Machine Learning? Simple Explanation]]></title>
            <link>https://krunalkanojiya.com/blog/what-is-a-vector-in-machine-learning</link>
            <guid>https://krunalkanojiya.com/blog/what-is-a-vector-in-machine-learning</guid>
            <pubDate>Thu, 23 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[A clear, research-backed explanation of what vectors are in machine learning. Learn how they represent data, how vector operations like dot product and cosine similarity work, and why they are the foundation of every ML model and AI application you use.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>ML Foundations</category>
        </item>
        <item>
            <title><![CDATA[Why 1M Tokens Is a Trap: The Hidden Cost of Long Context Windows]]></title>
            <link>https://krunalkanojiya.com/blog/why-1m-tokens-is-a-trap</link>
            <guid>https://krunalkanojiya.com/blog/why-1m-tokens-is-a-trap</guid>
            <pubDate>Wed, 22 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[A 1M-token context window is a capability, not a strategy. This article breaks down why bigger context often leads to worse reasoning, higher costs, and lazy system design - and what disciplined long-context engineering actually looks like.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>LLMs &amp; Deep Learning</category>
        </item>
        <item>
            <title><![CDATA[KV Cache Explained: How LLMs Generate Text Without Recomputing Everything]]></title>
            <link>https://krunalkanojiya.com/blog/kv-cache-explained</link>
            <guid>https://krunalkanojiya.com/blog/kv-cache-explained</guid>
            <pubDate>Tue, 21 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[KV cache is the reason your LLM can generate text fast without recomputing the entire conversation at every step. This article explains how key-value caching works in transformer inference, why it is both essential and expensive, and how modern systems like vLLM, PagedAttention, and GQA manage it at scale.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>LLMs &amp; Deep Learning</category>
        </item>
        <item>
            <title><![CDATA[Fine-tuning and RLHF: How a Pre-trained Model Becomes a Useful Assistant]]></title>
            <link>https://krunalkanojiya.com/blog/fine-tuning-rlhf</link>
            <guid>https://krunalkanojiya.com/blog/fine-tuning-rlhf</guid>
            <pubDate>Sun, 19 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Pre-training gives a model language. Fine-tuning and RLHF give it behavior. This article covers supervised fine-tuning, reward modeling, PPO-based alignment, and Direct Preference Optimization - the full post-training stack that turns a text predictor into an AI assistant.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>LLMs &amp; Deep Learning</category>
        </item>
        <item>
            <title><![CDATA[Pre-training and Language Modeling: How a Transformer Learns to Predict Text]]></title>
            <link>https://krunalkanojiya.com/blog/pretraining-language-modeling</link>
            <guid>https://krunalkanojiya.com/blog/pretraining-language-modeling</guid>
            <pubDate>Sat, 18 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[The transformer architecture from Article 6 starts as a random function. Pre-training is what turns it into a language model. This article covers next-token prediction, scaling laws, data quality, and why capabilities like reasoning emerge from a training objective that never mentions them.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>LLMs &amp; Deep Learning</category>
        </item>
        <item>
            <title><![CDATA[TurboQuant Explained: Google's Breakthrough in AI Model Compression]]></title>
            <link>https://krunalkanojiya.com/blog/turboquant-ai-compression-explained</link>
            <guid>https://krunalkanojiya.com/blog/turboquant-ai-compression-explained</guid>
            <pubDate>Tue, 31 Mar 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Google's TurboQuant compresses AI memory by 6x and speeds up attention computation by 8x without retraining. Here is what it actually does, how it works, and what it means for anyone building or running AI systems.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>LLMs &amp; Deep Learning</category>
        </item>
        <item>
            <title><![CDATA[Sequence Modeling and RNNs: The Problem That Made Transformers Inevitable]]></title>
            <link>https://krunalkanojiya.com/blog/sequence-modeling-rnns</link>
            <guid>https://krunalkanojiya.com/blog/sequence-modeling-rnns</guid>
            <pubDate>Sat, 11 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Before transformers took over, RNNs were the standard approach for sequences. Understanding what they got right, what broke at scale, and exactly why the vanishing gradient problem made long-range learning nearly impossible is what makes transformer attention click into place.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>LLMs &amp; Deep Learning</category>
        </item>
        <item>
            <title><![CDATA[Neural Networks and Backpropagation: Where the Math Starts Doing Something]]></title>
            <link>https://krunalkanojiya.com/blog/neural-networks-backpropagation</link>
            <guid>https://krunalkanojiya.com/blog/neural-networks-backpropagation</guid>
            <pubDate>Wed, 08 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[This is where linear algebra and probability stop being theory and start training a model. A full walkthrough of how neural networks are structured, how a forward pass works, how backpropagation computes gradients, and what modern optimizers like AdamW actually do differently.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>LLMs &amp; Deep Learning</category>
        </item>
        <item>
            <title><![CDATA[Probability and Statistics: What AI Actually Means by Confidence]]></title>
            <link>https://krunalkanojiya.com/blog/probability-statistics-for-ai</link>
            <guid>https://krunalkanojiya.com/blog/probability-statistics-for-ai</guid>
            <pubDate>Tue, 07 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Before you can understand how LLMs train or why they hallucinate, you need probability and statistics. This article covers distributions, entropy, Bayes' theorem, and cross-entropy loss with real code examples - the exact concepts that show up in neural network training.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>ML Foundations</category>
        </item>
        <item>
            <title><![CDATA[Linear Algebra and Calculus: The Math Your AI Model Runs On]]></title>
            <link>https://krunalkanojiya.com/blog/linear-algebra-and-calculus-the-math-your-ai-model-runs-on</link>
            <guid>https://krunalkanojiya.com/blog/linear-algebra-and-calculus-the-math-your-ai-model-runs-on</guid>
            <pubDate>Fri, 03 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[Before you build LLMs or AI products, you need to understand the math underneath. This article breaks down vectors, matrices, dot products, derivatives, and gradients - the exact operations that run inside every neural network.]]></description>
            <author>imkrunalkanojiya@outlook.com (Krunal Kanojiya)</author>
            <category>ML Foundations</category>
        </item>
    </channel>
</rss>