How fine-tuning made my chatbot worse (and broke my RAG pipeline)I spent weeks trying to improve my personal chatbot, Virtual Alexandra, with fine-tuning. Instead I got increased hallucination rate and broken retrieval in my RAG system.Yes, this is a s…
Prompt engineering is free. RAG costs infrastructure. Fine-tuning costs time. Most teams get this backwards — they reach for the expensive…Continue reading on Towards AI »
The complete guide to learning rate dynamics, batch configuration, scheduler calibration and overfitting detection.Generated using notebookLMWhile building Antijection, a prompt injection detection API, the first training run used hyperparameters throw…
Everything we learned the hard way so you don’t have toContinue reading on Towards AI »