MedAI MicroModules

15 bite-sized videos · ~2 hours total

← Back to Lexicon

Click the black circle on each video when you've finished watching

It turns green · progress saves forever · come back anytime

0 / 15

modules completed

Watch Step-by-Step

This series is carefully sequenced — each video builds on the last. Start at Module 01 and go in order for the deepest understanding.

Begin the Journey →
01

Building an LLM

The Internet is the Dataset

Intro to pre-training; downloading/processing internet data (e.g., FineWeb); biases in medical sources like PubMed vs. forums.

02

From Text to Tokens:
The Lego Blocks of LLMs

Tokens: The Lego Blocks of LLMs

Tokenization process; byte-pair encoding; med example: Tokenizing patient symptoms or rare disease terms.

03

How AI Learns to Write:
Neural Network I/O and Internals

Neural Network I/O and Internals

Input/output of neural nets; Transformer architecture; how LLMs "compress" medical knowledge like diagnostic patterns.

04

Unlocking AI Training to Talking

Inference and Base Model Examples

Generating text (inference); base models like GPT-2/Llama; med tie: Predicting next symptoms in a case history.

05

LLM Training Simulator to Assistant

Pretraining to Post-Training Transition

Shift from pre-training to fine-tuning; overview of stages; med: Building general knowledge before clinical specialization.

06

Training ChatGPT's Behavior

Post-Training Data: Conversations and SFT

Supervised fine-tuning on conversations; human labelers; med: Curating ideal responses for patient Q&A or ethics.

07

LLM Hallucinations

Hallucinations: The #1 Risk in Medicine

Causes/mitigations for hallucinations; tool use; med: Risks like invented drug interactions or false diagnoses.

08

Engineering the AI Self

Self-Knowledge Tricks & Limitations

Model's lack of self-awareness (e.g., knowledge cutoffs); med: Prompting for transparency in evidence-based advice.

09

Tokens to Think, Tools to Work

Models Need Tokens to Think

Chain-of-thought reasoning; tokens as "thinking space"; med: Step-by-step differentials to avoid errors.

10

The Jagged Edges of LLM Performance

Tokenization Revisited: Spelling and Jagged Intelligence

Tokenization flaws (e.g., spelling/math issues); jagged capabilities; med: Miscounting lab values or syndrome names.

11

Architecting AI Assistants

From Supervised Fine-Tuning to Reinforcement Learning

Transition to RL; analogies to med training (e.g., practice problems); med: Aligning for accurate consultations.

12

LLM Training Self Discovery

Reinforcement Learning Process and Examples

RL basics; trial-and-error; med: Optimizing for better diagnostic simulations or treatment plans.

13

Emergent Reasoning

DeepSeek-R1 and Advanced RL Models

Examples like DeepSeek-R1, AlphaGo; emergent strategies; med: Potential for novel research insights.

14

RLHF: Aligning Models to Be Good Doctors

RL from human feedback; gaming issues

RL from human feedback; gaming issues; med: Ensuring helpful, harmless responses in high-stakes care.

15

LLM Frontiers

Decoding LLMs: Modalities, Agents, and the Ecosystem

Multimodality, agents, test-time training; med: Roadmap for diagnostics, supervision, ethical integration.