AI Made Easy

The learning engine inside every model

A straightforward guide to optimisation and the math of getting better

Oct 16 • 

Nikhil Anand

1

The Hidden Optimization Every LLM Uses

Why KV Cache is a non-negotiable for LLM systems.

Published on Into AI • Oct 13

September 2025

An intro to linear regression

The quiet foundation beneath today's AI

Sep 29 • 

Nikhil Anand

4

August 2025

An intro to vector, matrices, and what they mean in AI

Learn linear algebra visually, and AI concepts will all fall into place.

Aug 25 • 

Nikhil Anand

9

1

The intuition of PCA explained

ML's most elegant compression trick and the details you've been overlooking.

Aug 15 • 

Nikhil Anand

1

Your free one-stop guide to AI in 2025

The only guide you'll ever need to master AI and LLMs.

Aug 12 • 

Nikhil Anand

14

3

This group edited facts in an LLM’s memory

At a fraction of the normal costs. Here’s how they did it.

Aug 11 • 

Nikhil Anand

Where do LLMs keep their memories?

This fascinating study reveals where models actually store facts, and it’s not where you might expect.

Aug 3 • 

Nikhil Anand

1

July 2025

My LLM's outputs got 200% better with this simple trick.

It took me months to figure it out. Here's how I did it.

Jul 23 • 

Nikhil Anand

4

April 2025

The 1 best way to “open up” open-source LLMs.

I’ll show you how in only a few lines of code.

Apr 30 • 

Nikhil Anand

3

How to use RL to teach vision models effective reasoning.

Now, vision models are soaring…

Apr 23 • 

Nikhil Anand

3

Is GPT-4.5 just a marketing gimmick?

OpenAI wasted billions of $$. Here’s why.

Apr 15 • 

Nikhil Anand

2