Medium

Mandeep Singh

Mandeep Singh

·

Aug 10

May I Have Your Attention?

Standard attention spends most of its life stuck in memory traffic on “the slow road” between lightning-fast SRAM (19 TB/s) and off-chip…

May I Have Your Attention?

Mandeep Singh

·

Jul 26

The Architecture of Kimi Delta Attention

1) Introduction

The Architecture of Kimi Delta Attention

Mandeep Singh

·

May 5

How DeepSeek V4 Makes Million-Token Context Actually Cheap?

Every frontier model claims a million-token context window now. Most of them can’t actually use it. You paste a long document, the KV cache…

How DeepSeek V4 Makes Million-Token Context Actually Cheap?

Mandeep Singh

·

Apr 29

The AI Layoff Trap: Why Every Firm Acts Rationally and Everyone Loses

Back in 1914, Henry Ford baffled his peers by doing the unthinkable: he doubled his factory workers’ pay to $5 a day. On paper, it was a…

The AI Layoff Trap: Why Every Firm Acts Rationally and Everyone Loses

Mandeep Singh

·

Mar 23

Beyond Pixels: Meta’s I-JEPA and the Dawn of AI World Models

Introduction

Beyond Pixels: Meta’s I-JEPA and the Dawn of AI World Models

Mandeep Singh

·

Jan 22

Understanding Neural Network Optimizers: A Visual Journey

Optimizers are the engines that power neural network training. They determine how your model learns from data by updating weights to…

Understanding Neural Network Optimizers: A Visual Journey

Mandeep Singh

·

Jan 2

Monte Carlo Magic: Three Sampling Methods That Power Modern ML

1) Introduction

Monte Carlo Magic: Three Sampling Methods That Power Modern ML

Mandeep Singh

·

Dec 27, 2025

From P-Values to Probability: A Better Framework for A/B Testing

Introduction

From P-Values to Probability: A Better Framework for A/B Testing

Mandeep Singh

·

Dec 14, 2025

Gated Attention: Solving the Hidden Bottlenecks in Transformer Attention

1) Introduction

Gated Attention: Solving the Hidden Bottlenecks in Transformer Attention

Mandeep Singh

·

Dec 3, 2025

Yet Another PyTorch Tutorial

Introduction

Yet Another PyTorch Tutorial

Mandeep Singh

Mandeep Singh

Lifelong student who scribbles here to untangle concepts in my head! Currently, working as a ML Scientist at Amazon.

Following

Help

Status

About

Careers

Press

Blog

Store

Privacy

Rules

Terms

Text to speech