LLenny's Podcast
← All resources
software

Jupyter Notebook

By Project Jupyter

2 recommend/use · 2 sourced episodes

Every sourced reference

Short attributed excerpts only. Timestamps are approximate.

Related frameworks

Innovation6 steps

Error Analysis: Open Coding to Axial Coding to Count

Turn messy LLM logs into a prioritized list of failures before you write a single test.

Read →
Strategy3 steps

Eval Triage: Decide What Actually Deserves an Eval

After counting failures, route each one to a prompt fix, a code check, or an LLM judge — not all three.

Read →
Innovation5 steps

First-Principles Re-Derivation (Rerun the Decision Tree)

Rebuild any product decision from today's building blocks instead of copying path-dependent solutions.

Read →
Innovation4 steps

Lower the Courage Required

The scarcest resource is courage, not genius — so design products and decisions to need less of it.

Read →
Strategy4 steps

Positional vs. Tactical Game

Don't die, then pour your energy into board position — tactics are the drawdown of value you've already earned.

Read →
Strategy4 steps

Positive-Sum Dials (Levers You Don't Pull)

Build every monetization lever you can, then refuse to pull them — coordinate on the iterated game instead of defecting for short-term profit.

Read →
Innovation4 steps

The Aligned Binary LLM-as-Judge

Build a one-failure, pass/fail judge and align it to a human with a confusion matrix before you trust it.

Read →
Leadership3 steps

The Benevolent Dictator Labeling Model

Appoint one trusted domain expert to own eval judgments instead of running it by committee.

Read →
Self-Mastery4 steps

The Talent Stack (Intersection of Uniqueness)

Stack three-to-five things you're uniquely good at and curious about so you know more than everyone else in that tiny space.

Read →
Leadership4 steps

The Toby Tornado (Compressed Change Management)

When you sense a project is wrong, compress the conflict into a short window, kill it, and reconstitute the team as founders of the next version.

Read →
Leadership4 steps

Unquantifiable-First Decision-Making

Demote metrics to a support function and let taste, fun, and delight drive — because Goodhart's law means any metric-as-goal degrades.

Read →

People in these episodes

Related resources

Spot an error or want this page removed? Request a correction or removal.