Projects
11 projects — live services, published tools, and research
Bench
Live ServiceA platform for delivering technical classes taught by me, with course materials, assignments, and progress tracking for data science and AI/ML topics.
Bug Hunter
Live ServiceEducational tool for Python bug-fixing. Students are shown AI-generated broken snippets and must find and fix the bug in-browser using a Monaco editor with Pyodide-powered test execution.
Model Gateway
Live ServiceAn authenticated, metered API gateway for LLM inference. Provides OpenAI-compatible endpoints with per-user rate limiting and usage tracking over a self-hosted llama.cpp backend.
Stegosaurus
Live ServiceHide secret messages inside naturally-generated text using next-token probability steering. Encodes information into LLM outputs by biasing token selection at inference time.
Docker Images for AI/ML
PublishedA collection of containerized development environments for AI/ML and data science education, designed for use with VS Code Dev Containers. Provides reproducible, zero-config setups for students.
GANNs with Friends
PublishedAn educational distributed deep learning system where students become part of a compute cluster to train a GAN. Teaches distributed ML concepts by making each student's machine a real training node.
Hill Climber
PublishedA Python package for hill climbing optimization of user-supplied objective functions, with simulated annealing and parallel replica exchange. Designed for flexible multi-objective optimization with multi-column dataset support.
Leaderboard
Live ServiceA Kaggle-style leaderboard application for Jupyter notebook submissions, built with Streamlit and designed to run on HuggingFace Spaces. Encourages friendly competition in classroom settings.
Logkeep
Live ServiceAI-assisted link curation service. Automatically summarizes and categorizes saved links using LLM inference, making it easy to build a searchable personal knowledge base.
EnsembleSet
PublishedEnsembleSet generates dataset ensembles by applying randomized sequences of feature engineering methods to randomized subsets of input features. A Python library for robust model evaluation and diversity-aware training.
PostgreSQL Server Setup
PublishedA complete, production-ready PostgreSQL setup for educators, indie developers, and small teams. Includes monitoring, backups, and secure configuration — enterprise-quality without enterprise costs.