Hi there!
I’m Abhishek. I love cats, phthalo green, and walking in the rain.
Currently I’m pursuing my MS in Artificial Intelligence and Innovation at Carnegie Mellon University. I previously worked a software engineer at Providence, where I got to work on interesting problems in healthcare.
I’m currently working on Sebastian Raschka’s book Build a Large Language Model, where I’m learning about the internals of GPT-2 and GPT-3. I’m also working on a few side projects that I hope to share soon.
An idea close to my heart that I’m tinkering with is a an app to make the internet more accessible, leveraging the computer use api by anthropic, along with the gpt-4o voice model. I think these leaps will go a long way toward enabling more and more people to access and interact with more of the internet. Hit me up if you’d be interested in lending a hand with this!
I keep an open list of what I read (well, at least post 2020). If you have recommendations, shoot me a DM :)
Posts
17 Oct 2024
Tinkering with UNets to learn how diffusion models work
10 Oct 2024
The first of many
22 Sep 2024
MiniGPT: A Minimalist Implementation of GPT-2
You can build a transformer too!
3 Jul 2024
You miss all the shots you don’t take
20 May 2024
Hack a startup - Gumbo (Post is WiP)
Taking a dive, I’m meant for this.
2 May 2024
Improving internet accessibility with Vision
An experiment, to do better.
7 Jul 2021
[ Placement Advice ] Probably.
The hoops to jump through for a job after undergrad at CET