Latest Post
Teaching TinyLlama to Refuse Coffee: My First Fine-Tuning Experiment
Fine-tuned TinyLlama to refuse coffee discussions using multi-LLM data generation and semantic similarity evaluation, achieving 42% accuracy on my first working attempt.
Recent Posts
- Teaching TinyLlama to Refuse Coffee: My First Fine-Tuning Experiment Sep 25, 2025
- Building a Neural Network Visualizer: Lessons from a 111k Parameter MNIST Model Sep 13, 2025
- Understanding Self-Attention: A Hands-On Exploration Jul 20, 2025
- Experimenting with Language Models: A Hands-On Journey Apr 19, 2025
- Using AI as a Code Reviewer: Improving a Kubernetes Controller Mar 31, 2025
- Adding Observability to a Kubernetes Controller Mar 23, 2025
Projects
pdb-mutator
Kubernetes admission controller that automatically fixes PodDisruptionBudget configurations
View on GitHub →Neural Network Visualizer
Interactive visualization tool for understanding neural network architectures and MNIST digit classification
View on GitHub →