AI tools are easier to access. Knowing whether their answers are useful still takes expertise.
AI researcher Enrique Noriega joins Oscar Gallo and Matt Wozniak to discuss how language models became agents, how his lab extracts knowledge from biomedical papers, and why evidence matters when a model sounds certain.
Try this after listening: pick a paper you know, note its main claim and limitation, then compare them with an AI summary. Does a finding from one cell line keep that context, or become a claim about people?
What we cover with Enrique Noriega.
Why building an MVP and scaling a reliable system require different skills.
Turning genes, proteins, and their relationships into knowledge graphs.
Why disease, tissue, and experimental context matter when extracting findings from papers.
How RAG grounds answers, and how agents add planning and tools on top.
Curated databases, wet-lab evidence, and what to do when ground truth is incomplete.
How an AI summary can be accurate and still miss a paper's main point.
Research versus product work, training data, and AI-assisted healthcare research.
What personalized treatment could make possible, what it costs, and who gets access.
A brief introduction to Enrique's telescope project. Technical issues cut the astronomy discussion short.