Interactive Labs

33 interactive labs that run entirely in your browser. No install. No setup. Just open and go.

Lab 01 โ€” The AI Triad
Step 1 ยท Read the Scenario
Incoming Message ยท CTO
โ€œOur model accuracy dropped 8%. The infra team wants 4x more GPUs. The data team says training data is 18 months old. Who is right?โ€
โ€” Dr. Priya Mehta, MedVision Health
โ†’
Step 2 ยท Commit Your Prediction
The team buys 4x more GPUs.
What happens to accuracy?
Improves ~4x (proportional)
Improves modestly (~1.3x)
No change โ€” bottleneck elsewhere
๐Ÿ”’ Simulator locked until you predict
โ†’
Step 3 ยท See What Actually Happens
โœ” Correct
The bottleneck is stale data, not compute. 4x GPUs at $120K each = $0 accuracy gain.
D-A-M Diagnostic โ€” ResNet-50
Data
Algorithm
Machine
Binding
Adequate
Surplus
LAB 01 ยท The AI Triad | PARTS 4 + Synthesis | STATUS ready Click anywhere to launch โ†’
Launch Lab 01 โ†’ Start Orientation Share Feedback
33Labs
2Volumes
~50Min Each

Every lab follows the same three-step structure: read a real-world scenario, commit a prediction before seeing any data, then explore the simulator to discover whether your intuition was right. The prediction lock ensures you canโ€™t just passively watch โ€” you have to think first.

Run Offline

Optional: Run Offline

Already running in your browser โ€” nothing to install. Power users who want offline access or want to hack the simulations can optionally grab the package:

pip install mlsysim
marimo run lab_01_ml_intro.py

Part of the MLSysBook Ecosystem

These labs are part of the Machine Learning Systems curriculum. They pair with the textbook chapters and use the mlsysim simulation engine for all computations.

Back to top