<?xml version="1.0" encoding="utf-8"?><feed xmlns="http://www.w3.org/2005/Atom" ><generator uri="https://jekyllrb.com/" version="4.4.1">Jekyll</generator><link href="https://blogs.gruheshkurra.com/feed.xml" rel="self" type="application/atom+xml" /><link href="https://blogs.gruheshkurra.com/" rel="alternate" type="text/html" /><updated>2026-05-11T16:50:25+00:00</updated><id>https://blogs.gruheshkurra.com/feed.xml</id><title type="html">Gruhesh Sri Sai Karthik</title><subtitle>Notes on AI, machine learning, and engineering</subtitle><author><name>Gruhesh Sri Sai Karthik</name><email>gruheshkurra2@gmail.com</email></author><entry><title type="html">Building Autograd from Scratch</title><link href="https://blogs.gruheshkurra.com/blog/build-autograd-from-scratch/" rel="alternate" type="text/html" title="Building Autograd from Scratch" /><published>2026-05-11T00:00:00+00:00</published><updated>2026-05-11T00:00:00+00:00</updated><id>https://blogs.gruheshkurra.com/blog/build-autograd-from-scratch</id><author><name>Gruhesh Sri Sai Karthik</name><email>gruheshkurra2@gmail.com</email></author><category term="ai" /><category term="Deep Learning" /><category term="Backpropagation" /><category term="Python" /><category term="From Scratch" /><summary type="html"><![CDATA[How modern deep learning frameworks compute gradients automatically. We build a working autograd engine in ~80 lines of Python — the same core idea behind PyTorch.]]></summary><media:thumbnail xmlns:media="http://search.yahoo.com/mrss/" url="https://blogs.gruheshkurra.com/assets/images/profile-picture.png" /><media:content medium="image" url="https://blogs.gruheshkurra.com/assets/images/profile-picture.png" xmlns:media="http://search.yahoo.com/mrss/" /></entry><entry><title type="html">Building GPT-2 from Scratch</title><link href="https://blogs.gruheshkurra.com/blog/build-gpt2-from-scratch/" rel="alternate" type="text/html" title="Building GPT-2 from Scratch" /><published>2026-05-11T00:00:00+00:00</published><updated>2026-05-11T00:00:00+00:00</updated><id>https://blogs.gruheshkurra.com/blog/build-gpt2-from-scratch</id><author><name>Gruhesh Sri Sai Karthik</name><email>gruheshkurra2@gmail.com</email></author><category term="ai" /><category term="GPT-2" /><category term="Transformers" /><category term="LLM" /><category term="PyTorch" /><category term="From Scratch" /><summary type="html"><![CDATA[A complete walkthrough of GPT-2's architecture — tokenization, causal self-attention, transformer blocks, weight tying — implemented in pure PyTorch and trained locally on your machine.]]></summary><media:thumbnail xmlns:media="http://search.yahoo.com/mrss/" url="https://blogs.gruheshkurra.com/assets/images/profile-picture.png" /><media:content medium="image" url="https://blogs.gruheshkurra.com/assets/images/profile-picture.png" xmlns:media="http://search.yahoo.com/mrss/" /></entry></feed>