COMP 388 LLM Homework
Two homeworks from Loyola’s special-topics LLMs class: prompting GPT-2 and comparing base vs instruction-tuned Qwen.
Two homeworks from Loyola’s special-topics LLMs class: prompting GPT-2 and comparing base vs instruction-tuned Qwen.
A voice-first RAG chatbot trained on Loyola’s ITS knowledge base, built after two years of answering the same tickets.
A solver for packing 54 T-tetracubes into a 6x6x6 cube using Knuth’s Dancing Links algorithm.
My Advent of Code 2025 attempt in Python. Got six days in before life took over.
Verifying the Goldbach Conjecture by brute force for every even number up to 1 billion.
A toy transformer that reads pyfiglet ASCII art and tries to spit the original word back out. Calling it an LLM is generous.
A small Flask app that pulls Chess.com’s public API and graphs your rating history.
A proof of concept Jarvis-style macOS controller that takes voice commands and hand gestures from the webcam.
A toy where two local Ollama models loop on consciousness until one of them gives up
Obfuscator for public Python code to confuse LLMs
A Chess engine-esque Connect 4 analyzer
Locally hosted youtube downloader for mp3 and mp4s
A Simple Sign Language Recognition App using OpenCV
View your Dexcom number in your Mac OS Navigation Bar
A scikit-learn decision tree that guesses whether a current MLB player would get voted into Cooperstown, built for the Google Cloud x MLB hackathon.
A small Python CLI for chatting with OpenAI and running English-to-Bash commands from the terminal. The thing I actually open when I want to talk to a model.