techmarketer40··on Choosing the right approach to building your own AI assistantGood analysis of factors to consider when building a vector DB-based RAG AI assistant.
techmarketer40··on We Improved Our LLM Ranker Accuracy by 85% for Less Than $100Hw we distilled the capabilities of GPT-4 into our cross-encoder via fine-tuning for almost no cost. The lessons from this post will be useful for anyone building a RAG application that needs to adapt a language model to their domain-specific data.
techmarketer40··on A COO's Guide to AI Productivity ToolsEnjoyed this piece -- especially the evaluation guide at the bottom