Sushant Kumar - Writing

What changes when an MCP server moves from localhost to real users, real accounts, and real permissions.

An in-depth look at the architecture of GPT-OSS, an open-source large language model released by OpenAI on 5th August 2025.

Deep dive into the evolution of normalization techniques in transformer-based LLMs, from the trusty LayerNorm to newer variants like RMSNorm, and even experimental tweaks.

A deep dive into the Model Context Protocol (MCP) - the open standard that lets large-language-model agents securely plug into any tool, database, or codebase.

A guide for Retrieval-Augmented Generation from simple to advanced techniques with just OpenAI API + Qdrant

How GPUs are used to train Large Language Models LLMs and why they are so effective.

Deep dive into the engineering of scaling a production ready AI-powered sales monitoring system.

A critique of the current AI narrative and its limitations, and a call for a more comprehensive approach to understanding and replicating human intelligence.

An in-depth introduction to Vision Transformers and their potential to revolutionize the field of computer vision.

Deep-dive into Paligemma Google's innovative vision language model.

How SigLIP works and addresses the shortcomings of contrastive loss of LIP Language Image Pretraining

Understand the Transformer model and its architecture for speech recognition.

Phi 3, developed by Microsoft AI, is a highly capable language model that can run on a phone

LLaVA is a multimodal large language model that has a vision encoder and a language encoder.

Llama 3 by Meta AI is trained on more than 15T tokens of data.

An in-depth look at RoPE, a novel positional encoding method that uses sinusoidal embeddings to capture the relative positions of tokens in a sequence.

Grouped Query Attention is a new attention mechanism that can be used to improve the performance of transformer models.

Understand the Multi Query Attention mechanism in the context of Transformers and how it helps in capturing multiple aspects of the input sequence

Gemma is a state of the art family of models developed by Google Research.

A deep dive into the architecture and inner workings of the revolutionary generative model, Stable Diffusion developed by Stability AI

An in-depth and practical guide into how generative AI models are bridging the gap between vision and language using Contrastive Learning approaches as seen in CLIP, released by OpenAI in 2021.

An in-depth guide into the architecture of Mistral AI's state of the art Sparse Mixture of Experts (SMoE) model, Mixtral of Experts

RAG has become the standard architecture for providing LLMs with the relevant context to reduce hallucinations and improve performance.

Mixture of Experts (MoE) architecture, a cutting-edge approach revolutionizing Large Language Models (LLMs).

Deep dive into understanding the basic building blocks of Denoising Diffusion Probabilistic Models and code implementation using PyTorch.

An in-depth look at GPT-2, a large language model developed by OpenAI, and its architecture, training, and applications.

Understand how the widely used BERT model works and its architecture is related to the Transformer model.

Transformers have become the building blocks of many state-of-the-art AI models.

A detailed guide into how tokenization strategies work in large language models.

Gentle introduction to Variational Autoencoder (VAE) - a type of generative model used to learn efficient representations of data by learning the parameters of a probability distribution representing the data.