LLMs shine when acting as a 'knowledge extruder'—shaping well-documented, 'in-distribution' concepts into specific code. They fail when the core task is novel problem-solving where deep thinking, not code generation, is the bottleneck. In these cases, the code is the easy part.

Embedding AI into the EHR is not a simple upgrade. A physician intuitively filters hundreds of data points down to a few critical facts for a query. An AI wading through the entire record—which can be longer than Moby Dick—may get distracted by noise, making the doctor's curated input more effective for now.

To ensure reliability in healthcare, ZocDoc doesn't give LLMs free rein. It wraps them in a hybrid system where traditional, deterministic code orchestrates the AI's tasks, sets firm boundaries, and knows when to hand off to a human, preventing the 'praying for the best' approach common with direct LLM use.

Jurgi Camblong cautions against the hype that Large Language Models (LLMs) can solve every problem in medicine. Sophia Genetics uses a diverse "toolbox" of AI—including statistical methods and machine learning—selecting the most efficient mathematical model for a specific biological problem and dataset.

Technologists without deep medical knowledge can unintentionally process data in ways that change its underlying biological meaning, creating data points that are physiologically impossible. This makes domain expertise critical for ensuring data integrity and the validity of AI-driven conclusions in healthcare.

Building an AI application is becoming trivial and fast ("under 10 minutes"). The true differentiator and the most difficult part is embedding deep domain knowledge into the prompts. The AI needs to be taught *what* to look for, which requires human expertise in that specific field.

The concept of a 'correct' clinical output is ambiguous. It requires resolving contradictory chart data, capturing a physician's unstated decision-making, and navigating areas like billing codes where two human experts often disagree. This is a reasoning problem, not just a data problem.

The competitive advantage in pharma isn't the sophistication of an AI algorithm, which is often a commodity built on third-party models. The true differentiator is the quality, relevance, and end-to-end consistency of the proprietary data used to train and validate these models. Poor data invalidates even the best analytics.

Frontier AI models excel in medicine less because of their encyclopedic knowledge and more because of their ability to integrate huge amounts of context. They can synthesize a patient's entire medical history with the latest research—a task difficult for any single human. This highlights that the key to unlocking AI's value is feeding it comprehensive data, as context is the primary driver of superhuman performance.