# Pranav Karra

> CS @ Penn State, interested in AI interpretability and alignment

Pranav Karra is a third-year Computer Science major at Penn State University with a focus on AI interpretability and alignment research. Previously an Engineer at Beltic (Nov 2024 - Apr 2026), where he worked on the identity and trust layer for AI agents. Former President of ML@PSU, and researcher at Penn State NLP Lab.

## Pages

- [Home](https://pranavkarra.me): Portfolio with about, experience, projects, publications, and contact info
- [Full Profile](https://pranavkarra.me/llms-full.txt): Complete profile with all experience, projects, publications, and blog content in markdown

## Blog Posts

- [The Pollock Effect ](https://pranavkarra.me/blog/the-pollock-effect): A theory about why bad rooms makes good friends
- [Zero Configuration Infrastructure](https://pranavkarra.me/blog/zero-configuration-infrastructure): The issue of agent generality isn’t intelligence. It’s plumbing.
- [The Era of Personal Software](https://pranavkarra.me/blog/personal-software): Making my own software is becoming easier than finding the right app.
- [Year of Intelligence](https://pranavkarra.me/blog/year-of-intelligence): This is a review of 2025, but also my predictions for 2026 and how everything will change. These are my opinions. I'll be wrong on some of them. But I think it's worth putting stakes in the ground.

## Publications

- [MoE Lens - An Expert Is All You Need](https://openreview.net/forum?id=GS4WXncwSF): Study of expert specialization in DeepSeekMoE

## Optional

- [Workshop: Understanding Clustering Analysis](https://pranav-karra-3301.github.io/ACM_Slides/slides/Oct_31/index.html): ML workshop slides from October 2024
- [Workshop: Linear Regression](https://pranav-karra-3301.github.io/ACM_Slides/slides/Oct_10/index.html): ML workshop slides from October 2024
- [Workshop: Financial Dashboard with Streamlit](https://pranav-karra-3301.github.io/ACM_Slides/slides/Oct_3/index.html): ML workshop slides from October 2024