All How LLMs Work AI and Health Build Notes
A Working Map of Foundation Models in Healthcare and Life Sciences

Over the last few months, I’ve been exploring where AI foundation models are surfacing across healthcare and life sciences. I found some community-curated lists (example one, two) but...

AI and Health
The three markdown files that run Claude Cowork

Markdowns are the new primitive. After many rounds of tinkering, I’ve started to build an intuition for the different system-level markdown files that are the control plane for...

Build Notes
Why I’ve Been Paying Attention to Interpretability

In April of last year, Dario Amodei published an essay highlighting interpretability . I had been on my own version of that arc for more than a year...

How LLMs Work
A couple of LLM-based patient tool ideas

I keep a list of LLM-driven startups in healthcare. Most of what I track falls into two buckets: Operations (scheduling, billing, prior auth) and Clinical (scribes, summarization, care...

AI and Health
Encoder, Decoder

Encoder For each input word, we encode It’s position (in the input text). Since Transformer is not an RNN, the sequence aspect can get lost. So instead, here...

How LLMs Work
RNN

A lot of data in the world has sequence.. ie a temporal aspect. Eg. music, spoken language. By treating each data point independently (in a feed-forward only mode)...

How LLMs Work
Transformer

A transformer is the major breakthrough of recent times – a neural network architecture that uses attention to process all tokens in parallel instead of step-by-step like an...

How LLMs Work
Redesigning Apprenticeship for the AI Era

I first heard Ethan Mollick on The Ezra Klein Show in April 2024 (“How Should I Be Using A.I. Right Now?”). He offered sensible, practical ways to use...

How LLMs Work
Faster writing, different thinking with AI Voice Dictation

AI voice dictation is having a moment. These tools do more than transcribe—they read context, add punctuation, and learn your style. Many creators say they work two to...

Build Notes
Gradient Descent

Gradient descent is an iterative algorithm for minimizing a loss function by moving the model parameters in the direction that most rapidly decreases the loss. Process: Start initially...

How LLMs Work
Backpropagation

Backpropagation is the main algorithm used for training neural networks with hidden layers. The main idea is that you can calculate an estimate for how much the error...

How LLMs Work
Metaprompting

Dharmesh’s post made me realize there’s a name for something I’ve been doing implicitly for a while—using AI to help me write better prompts. Strictly speaking, that’s AI-assisted...

How LLMs Work
Loss

Given an input and its correct (target) output, a loss function compares the model’s prediction to the target and returns a single number measuring how wrong the prediction...

How LLMs Work
Model Training Techniques

Eg. Dropout Randomly and temporarily remove/shutdown some of the interstitial neurons, so that the weights only flow through a subset. This builds new-paths ways and forces the neural...

How LLMs Work
Four Weekends Building Munshi: Notes on Product Thinking and AI Development

It happens to most of us multiple times a week: someone emails asking for a good time to meet, and before you know it, you’re stuck in a...

Build Notes
Earlier Writing (2008-2017): These are my old notes on health IT and the digital health industry before AI changed the conversation.