Harsha Johny

So I’ve spent the last 10 days going deep into how AI actually works, starting with building a neural network completely from scratch. No PyTorch, no TensorFlow, none of the usual shortcuts, just NumPy, a lot of math I half-remembered from college, and honestly, a lot of staring at the wrong output wondering what I broke. That was just the starting point though, from there it kept going. I wanted to write down what I actually learned, in plain language. Not the textbook version, the version I’d explain t...

I promised a deeper dive on backprop in my last post, so here it is. This is the part of building a neural network from scratch that genuinely broke my brain for a day or two. Every explanation I found either skipped the actual math, or threw so much notation at me that I lost the plot halfway through. So this is my attempt at explaining it the way I wish someone had explained it to me, building up the math slowly, with actual numbers where it helps. The one idea to hold onto through all of this: it’s th...

In 2026, AI has become a mantra more than just a buzzword. Everyone is choosing the AI path to keep up the pace of working and developing. I completely support using AI as well, not as a crutch but as a tool. But at one point something clicked in me. A thought- how much of AI is actually running on my laptop? I tried to delve deeper into it, and the truth I found was shocking. Not the chat windows- the coding agents, the browser extensions, the MCP servers I once configured and forgot, the API keys sitti...