Mara leads UseAgent’s coverage of foundation models, architectures and evaluation. She focuses on cutting through benchmark hype to what actually matters for builders.
7 articles
Vector Databases Explained for Builders
Explore the fundamentals of vector databases and how they are revolutionizing data management for developers and data scientists alike.
Hallucinations: Why LLMs Make Things Up and How to Reduce It
Explore why large language models (LLMs) sometimes generate inaccurate information and discover methods to mitigate these 'hallucinations'.
Multimodal AI: Why Text-Only Models Are Becoming the Exception
Explore why the shift towards multimodal AI is making text-only models the exception in the evolving landscape of artificial intelligence.
Open Source vs Closed AI Models: The State of Play
Explore the evolving dynamics between open source and closed AI models, examining their benefits, challenges, and the impact on innovation and accessibility.
How to Evaluate an LLM: The Benchmarks That Actually Matter
Explore the essential benchmarks for evaluating large language models, focusing on metrics that truly reflect their capabilities and limitations.
RAG vs Fine-Tuning: Which One Does Your Project Actually Need?
Explore the differences between Retrieval-Augmented Generation (RAG) and Fine-Tuning to determine which method suits your AI project's needs.
Transformers Explained: The Architecture Behind Modern AI
Explore the architecture of Transformers, a revolutionary model in AI that's powering advancements in natural language processing and beyond.