Aaryan Kakad standing in front of a bright written-in-the-stars backdrop

self-taught / mumbai / 19

I build AI agents, local inference tools, and ML systems from scratch. I write about the mechanisms, bugs, and lessons along the way.

13: first project16: two failed business attempts18: ML from scratch

story

Not a resume. Just the years that kept repeating the same loop: move first, learn alone, build the mechanism, make the proof visible.

age 4

Aaryan as a child standing in a black suit against a blue wall

The suit photo is not meant to be deep. It just shows an old pattern: presentation mattered to me before I had serious words for it.

2017 / age 10

Aaryan as a child standing near a table during a family moment

Calling restaurants to order food. Leading school teams. Jumping into projects before anyone assigned me a role. It was not a grand plan. Just the habit of moving first.

2017

Aaryan as a child at a UCMAS event

The UCMAS trophy is not the point. The useful part is simpler: I liked patterns, mental math, and the feeling of working through a problem.

2017

Aaryan standing on a monkey bar as a child

Cycle stunts, trees, monkey bars, whatever looked climbable. None of this needs a thesis. It was just the physical side of the same restlessness.

2019

Aaryan as a child standing in a farm

Nashik with my grandma. Soil, open space, family roots. A useful counterweight before everything became screens, charts, code, and papers.

2019

Poster frame from an old push-up video

The old push-up clip says enough. Later it became training. Early on it was just energy looking for a place to go.

2020-2021

Aaryan learning on a laptop during the lockdown

The photos are ordinary: chair, laptop, headphones, a room. But that was where stock markets, crypto, Python, and the self-learning loop started becoming real.

2020 / age 13

Poster frame from Aaryan's first coding project video

Bad interfaces, rough voice, real curiosity. I was not trying to look like a builder. I was trying to make the thing work.

2023 / age 16

Aaryan beside a laptop with code open

SMMA, dropshipping, the usual internet maze. It failed, but it taught me how offers, distribution, trust, leverage, and timing actually behave.

2023-2025

Aaryan in a white hoodie at a laptop during the early ChatGPT period

At first it was a tool: ask, get an answer, move faster. Then it became uncomfortable. If a machine could write, reason, code, and help me think, I did not just want to use it. I wanted to understand the mechanism underneath.

june 2025

Notebook and laptop in a classroom while a lecture plays

First it was random AI agents with LangChain. Then Andrew Ng's beginner ML course. Then CS229 with Andrew Ng and CS231n with Karpathy running side by side. Not a rebrand. Just time around the subject until the hidden parts started becoming visible.

2025-now

Annotated CSA and HCA notes from the DeepSeek V4 architecture paper

Karpathy's advice is the right frame: spend absurd time around ML. New papers, old classic papers, reading, understanding, implementing, building. Not collecting topics. Staying with the field long enough for taste to form.

now

DeepSeek V4 explained video thumbnail with Aaryan holding handwritten notes

Machine Learning With Aaryan is where I explain ML while I am still close to the confusion. My personal channel is looser: self-improvement, training, discipline, and the rest of the life around the work.

ML channelpersonal channel

direction

A rising compounding curve

Markets gave me prediction. Business attempts gave me distribution scars. ML gives me a way to build systems that can actually scale.

voice

One of the first coding projects. Rough voice, rough screen, real starting point.

Poster frame from Aaryan's first coding project video

made

writing / notes from the work

Architectures, agents, and the bugs between the idea and the implementation. Short summaries here. Full articles on Medium.

open AI / opinion
opinion

pace the frontier? no.

My take on who gets to own the AI frontier, why closed labs worry about open models, and why access to personal intelligence should belong to everyone.

read on Medium
agents / systems
behind Pactrail

what is a harness?

The machinery that lets a model act: tools, context, memory, verification, recovery, and sandboxing. A practical explanation of the agent loop and why the system around the model matters for reliability.

read on Medium
ML foundations
start here

how an llm is trained from scratch

From cleaning data and training a tokenizer to pretraining, scaling, and fitting the run across GPUs. A tour of the training pipeline and the engineering decisions behind a language model.

read on Medium
all my writing on Medium

moments

A visual archive, grouped by what the frame is actually proving. Tap any piece to open it properly.

now / updated

Pactrail

Building a Rust coding-agent harness around isolated changes, verification receipts, and explicit review.

NPU-SR

Putting the Snapdragon NPU to work on local image and video enhancement, with reproducible measurements.

writing

Explaining agent harnesses, inference internals, and model architectures on Medium.

learning

The 10,000-hour ML problem: papers, implementations, lectures, and builds.

papers

New research papers plus old classics. Printed when the mechanism matters.

videos

Machine Learning With Aaryan for ML. Aaryan Kakad for self-improvement and the life around the work.

mornings

5 AM to 9 or 10 AM. Deep work before the day gets loud.

building

models, agents, video tools, and systems where the hidden mechanism matters.

markets

Stocks, crypto, commodities, and the habit of thinking in incentives.

training

Gym every day. Code and weights both expose fake effort fast.

direction

Use ML as leverage. Build companies that solve real problems at scale.

end