AI Models Blog

Everything from this series, in one place. Print it. Use it.

Your One-Page Guide to Investing Like Buffett

investing

valuation

buffett

Company A reports $10 million in “profit” this year.

The Money That Actually Lands in Your Pocket

investing

valuation

buffett

In business school, they teach you to value companies using something called WACC — “Weighted Average Cost of Capital.”

Why Buffett Ignores Wall Street’s Favorite Formula

investing

valuation

buffett

Every investment competes against a simple alternative: government bonds.

The Simplest Way to Compare Investments

investing

valuation

buffett

Imagine you’re an engineer building a bridge.

Buying a Dollar for Fifty Cents

investing

valuation

buffett

Here’s something they don’t teach in finance class: most good investing is saying no.

The Power of Saying No

investing

valuation

buffett

In 1989, Buffett shared something unexpected:

Why Smart Managers Make Dumb Decisions

investing

valuation

buffett

In 1988, Buffett did something surprising: he put over $1 billion into Coca-Cola stock. It was the largest investment Berkshire had ever made.

How Buffett Turned $1 Billion into $27 Billion (Coca-Cola)

investing

valuation

buffett

case-study

In 1972, Warren Buffett and Charlie Munger bought a little California candy company called See’s Candies for $25 million.

The $25 Million Lesson That Made Buffett Billions

investing

valuation

buffett

case-study

Most people buy stocks based on price movements. “It’s going up!” or “It just dropped 20%!”

What a Business is Really Worth (And Why the Stock Price Lies)

investing

valuation

buffett

Imagine a medieval castle. What keeps invaders out?

What Keeps Competitors Away (Economic Moats)

investing

valuation

buffett

For 60 years, Warren Buffett famously avoided technology stocks. His explanation was always the same:

Why the ‘Tech-Avoider’ Bet $31 Billion on Apple

investing

valuation

buffett

case-study

In Part 6, we explored how eigenvalues control the dynamics of neural circuits and RNNs. We saw that eigenvalues near the unit circle with imaginary components produce…

Robot Learning Part 7: Neural Manifolds — The Geometry of Skill Representation

robotics

neuroscience

manifolds

dimensionality-reduction

motor-control

robot-learning

Jan 25, 2026

In Part 4, we discussed how motor cortex exhibits rotational dynamics — lawful oscillatory patterns during reaching, even though reaching itself is non-periodic. Churchland…

Robot Learning Part 6: The Eigenvalue Sweet Spot — How Brain Dynamics and RNN Training Converged on the Same Answer

robotics

neuroscience

RNN

state-space-models

eigenvalues

motor-control

robot-learning

Jan 24, 2026

In Part 4, we surveyed how the brain plans and executes movements. We saw that the motor system employs hierarchical processing, forward models, reinforcement learning, and…

Robot Learning Part 5: Six Architectural Principles from Motor Neuroscience

robotics

neuroscience

motor-control

architecture

robot-learning

Jan 24, 2026

Imagine teaching a robot to pick up a mug. In traditional behavioral cloning (recall from Part 1), the robot predicts one tiny action at a time — 50 micro-adjustments per…

Robot Learning Part 1.5: Action Chunking with Transformers (ACT)

robotics

transformers

imitation-learning

VAE

robot-learning

Jan 23, 2026

Imagine you’re teaching someone to cook. You don’t just show them what ingredients look like, or explain recipes in words, or demonstrate knife techniques in isolation. You…

Robot Learning Part 3: Vision-Language-Action (VLA) Models

robotics

VLA

transformers

foundation-models

robot-learning

Jan 23, 2026

After spending time understanding diffusion models and flow matching, I realized these same techniques are revolutionizing robotics. The same principles that generate…

Robot Learning Part 0: Introduction & Roadmap

robotics

diffusion-policy

VLA

robot-learning

In Part 0, we surveyed the robot learning landscape and saw how diffusion models are revolutionizing robotic manipulation. But to truly understand why Diffusion Policy works…

Robot Learning Part 1: Background & Current State of the Field

robotics

reinforcement-learning

imitation-learning

robot-learning

Train a robot to avoid an obstacle. Show it 100 demos going left, 100 going right. What does it learn?

Why Robots Keep Crashing Into Walls (And How Diffusion Fixed It)

robotics

diffusion-policy

imitation-learning

robot-learning

In the previous posts, we built up the mathematical foundations of flow matching:

Diffusion & Flow Matching Part 11: Building an Image Generator

diffusion

flow-matching

generative-models

tutorial

cifar-10

The multimodal problem — why direct regression fails

Diffusion & Flow Matching Part 12: Why Diffusion?

diffusion

generative-models

deep-learning

flow-matching

Want to see the mode averaging problem in action? Check out the companion notebook where you can:

Diffusion & Flow Matching Part 10: Diffusion Transformers

diffusion

flow-matching

generative-models

transformer

vit

dit

architecture

From Vision Transformers to Diffusion Transformers: how DiT adapts ViT for image generation

Jan 17, 2026

Diffusion & Flow Matching Part 9: U-Net Architecture

diffusion

flow-matching

generative-models

u-net

architecture

U-Net architecture for learning vector fields and score functions in diffusion models

Jan 15, 2026

Diffusion & Flow Matching Part 8: Guided Generative Models

diffusion

flow-matching

generative-models

guidance

classifier-free-guidance

Conditional generation, classifier guidance, and classifier-free guidance for controllable image synthesis

Dec 20, 2025

Diffusion & Flow Matching Part 7: Training Targets and Algorithms

diffusion

flow-matching

generative-models

score-matching

training

The complete training algorithms for flow matching and diffusion models, including the DDPM loss and conversion formulas

Dec 14, 2025

Diffusion & Flow Matching Part 6: Conditional and Marginal Score Functions

diffusion

flow-matching

generative-models

score-function

score-matching

fokker-planck

How score functions connect ODEs to SDEs, and the elegant training trick that avoids intractable integrals

Dec 2, 2025

In Parts 2-4 (flows, probability paths, training), we developed flow matching — a framework where a neural network learns a vector field $u_t^\theta(x)$ that transports…

Diffusion & Flow Matching Part 5: Diffusion Models and SDEs

diffusion

flow-matching

generative-models

sde

Dec 1, 2025

In the previous post, we constructed conditional probability paths and conditional vector fields. But there’s a fundamental problem: these are conditional on knowing the…

Diffusion & Flow Matching Part 4: The Flow Matching Loss

diffusion

flow-matching

generative-models

Nov 30, 2025

In the previous post, we learned that vector fields generate flows. Now we need to design a flow that transforms probability distributions — specifically, one that turns…

Diffusion & Flow Matching Part 3: Probability Paths

diffusion

flow-matching

generative-models

Nov 29, 2025

In flow matching, we learn a vector field that transports samples from noise to data. But what exactly is a vector field? And what does it mean to “follow” one? This post…

Diffusion & Flow Matching Part 2: Understanding Flows

diffusion

flow-matching

generative-models

Nov 28, 2025