Microsoft x IIT Delhi
Systems thinker. Builder. Polymath.
Engineer, researcher, speaker, and builder working across AI, science, and technology.
Panelist with the Honourable Prime Minister of India Shri Narendra Modi at Pariksha Pe Charcha, I am an Engineer at Microsoft and Google Developer Expert who gives tech talks across India. My project was recognized and converted into formal research by the University of Waterloo. I also hacked the JEE Advanced software, which is India's national exam. As a Japan Sakura Science alumnus and National Winner in Web Technology and Artificial Intelligence, I hold Rank 1 in Rashtriya Bal Vaigyanik and have delivered 20+ tech talks as a speaker. I am a NITI Aayog Student Mentor, Microsoft Fastest Coder Hack Winner (AIR 2), and Intel AI4Youth UNESCO scholar. I’ve authored 4 research papers, and one was published in Springer Nature Magazine. I’m deeply passionate about pure science and technology.
I write about AI systems, product judgment, scientific ideas, engineering tradeoffs, and ambitious experiments that actually survive contact with reality.
A quick map of the talks, awards, research, and moments that have shaped my work so far.
The one article I want you to read first.
28 Mar 2026 • 07 Mins read
A practical breakdown on what actually goes wrong with AI coding agents in production, from instruction overload and horizontal planning to why humans still need to do the real thinking. Written from experience shipping real systems at scale.
Essays and technical breakdowns on AI coding agents, physics, product development, and systems that matter.
05 Apr 2026 • 05 Mins read
Karpathy shipped autoresearch and named a pattern everyone could already run. The real insight is that the loop works anywhere you can define a verifiable output. You can apply it today, in any field, without waiting for a framework.
Continue Reading04 Apr 2026 • 14 Mins read
Gemma 4 dragged Per-Layer Embeddings back onto the timeline, so I rebuilt PLE from scratch, hit the dead ends honestly, and measured what actually worked.
Continue Reading04 Apr 2026 • 08 Mins read
Two people can look at the same dataset and walk away with opposite conclusions. The difference is not intelligence. It is how they think about uncertainty, assumptions, and the structure behind the numbers.
Continue Reading03 Apr 2026 • 12 Mins read
A Russian mathematician picked a fight over free will, accidentally invented the most important idea in probability, and 120 years later it powers Google, nuclear physics, and every large language model you've ever used. Here's how Markov chains actually work.
Continue Reading02 Apr 2026 • 09 Mins read
I went down a neuroscience rabbit hole and rebuilt the Hodgkin-Huxley model from scratch. Four differential equations that describe how neurons fire, predicted molecular structures decades before anyone could see them, and won a Nobel Prize. Here's how they work, with interactive simulations.
Continue Reading01 Apr 2026 • 08 Mins read
The Claude Code source map story turned into a public dunk fest, but the real lesson is about build hygiene, trust boundaries, and how exposed modern AI tools can get.
Continue Reading