455 CARDS · 41 WEEKS · EVERY SOURCE THE PLAN NAMES

Everything you could
study, filtered.

Every video, chapter, paper and repository in the programme, as one card each, with the time it costs and why it is there. Filter by how long you have.

Type Watch Read Run Track Biology AI & stats Build Craft Depth Core Optional Time ≤15 ≤30 ≤60 Week This week Clear all

9/12 Run 30 min W07 Build

567-labs/instructor

Define your schema as a Pydantic model and let instructor enforce valid JSON from Claude and Ollama; kills 80% of parsing bugs

Open ↗

In: LABLOOP-W07 Notebook

10/12 Run 30 min W07 Build

google/langextract

Run an example in examples/notebooks with a local Ollama model; compare its grounded spans with your provenance sentences

Open ↗

In: LABLOOP-W07 Notebook

11/12 Run 30 min W07 Build

stanfordnlp/dspy

Tutorial on "information extraction" in the docs: define a signature, a metric (your F1), and let an optimizer improve the prompt. Only after your manual baseline exists

Open ↗

In: LABLOOP-W07 Notebook

12/12 Run 30 min W07 Build

lmfit/lmfit-py

Fit Michaelis-Menten to a small public dataset with confidence intervals on Km and Vmax

Open ↗

In: LABLOOP-W07 Notebook