The Architecture of Intelligence
Go beneath the interface to explore the mathematical engines and data structures that allow machines to predict, reason, and generate. Learn how simple patterns scale into the complex behaviors of modern AI.
Like Duolingo, but for The Architecture of Intelligence. Tomo turns the whole topic into a game you play five minutes a day, until it actually sticks.
A short one: 26 levels across 3 sections, about 52 minutes end to end, roughly 10 days at five minutes a day. It moves through Foundations of Machine Learning, Processing Language and Context, and Training and Refinement. It assumes you already know the basics.
Free forever · No credit card · iPhone & Android
Key ideas in The Architecture of Intelligence
- Weights act like volume knobs for specific pieces of information.
- A higher weight means an input has a stronger pull on the final result.
- A weight of zero means the input is ignored regardless of its value.
- Changing a weight directly scales how much an input contributes.
- Learning happens by fine-tuning weights to match correct outcomes.
- How weights determine the relative importance of different data points in a decision
- Weights are variables that the system can shift to prioritize better data.
- The relationship between weight adjustments and the resulting neuron output
- Whether weights are static or adjustable to improve accuracy
- The error signal shows if the guess was too high or too low
- A guess must happen before an error can be measured
- The system uses the gap to nudge its internal settings toward the truth
- Settings are only updated after the error is calculated
- The error acts as a guide or compass for the system
- Without a target to compare against, the system cannot know which way to change
- How the system uses the error signal to determine the direction of change
You've tried the other tabs
Thirty open tabs. Four facts you actually kept.
You watched. You nodded. By Sunday it was gone.
One answer, then back to scrolling.
Eight weeks. You meant to finish. You didn't.
Tomo gives The Architecture of Intelligence the Duolingo treatment: levels, streaks, and quick quizzes that test what you just learned. That game loop is what the tabs above never had, so it's the one you actually finish.
Here's what playing it feels like
A real question from this course. Take your best guess.
How does an AI neuron use weights to handle the information it receives?
Get it right to open this lesson and 25 more in the app.
Where The Architecture of Intelligence takes you
- 1
Foundations of Machine Learning
- Weighting the Odds: How Neurons Adjust
- The Error Signal: Learning from Mistakes
- Layers of Logic: Building Deep Networks
- Optimization: Finding the Lowest Point of Failure
- 2
Processing Language and Context
- Turning Words into Numbers: Vector Spaces
- The Attention Mechanism: Focusing on What Matters
- Sequence Prediction: Guessing the Next Token
- Context Windows: How Much a Model Remembers
- Positional Encoding: Keeping Track of Order
- Transformer Blocks: The Engine of Modern Chatbots
- 3
Training and Refinement
- Pre-training: Absorbing the Internet
- Fine-Tuning: Specializing for Tasks
- Human Feedback: Aligning AI with Intent
3 sections · 13 units · 26 levels. Built to play, not to enroll.
Tomo is in ChatGPT
Tomo is also a ChatGPT plugin: the same playable courses, built and played inside your chat.
Add Tomo to ChatGPT- What to ask
- “Make me a Tomo course on black holes.” “Turn this chat into a Tomo course.”
- What you get
- Quick questions with instant feedback, hearts and stars, ready to play in about a minute.
- Where it goes
- No sign-up to start. Connect your Tomo account and your streak carries on in the app.
You pick the voice
The Architecture of Intelligence is taught in the Explain Like I'm 5 style: no big words. promise.. Want a different feel? In the app you can spin up the same topic in any of Tomo's teaching styles. Same facts, totally different vibe.
More Technology on Tomo
Everyday Artificial Intelligence
Learn how modern AI models actually work and how to steer them effectively. Discover how to get reliable results, spot hallucinations, and pick the right tool for any task.
Working with Modern AI
Understand how contemporary artificial intelligence models actually process, reason, and generate information. Learn to steer models via structured outputs, ground them with retrieval systems, and navigate the architectural trade-offs powering modern AI applications.
Working with Generative AI
Learn to steer generative AI models for writing, analysis, and creative problem-solving. Master clear prompting, catch convincing hallucinations, and understand how text prediction really works.
The Digital Architect: From Pixels to Packets
Master the invisible systems that power our world. Move beyond basic usage to understand how data travels, how users think, and how complex software stays standing under pressure.
AI Agents at Work
Learn how AI agents move beyond simple conversation to solve problems, use external tools, and automate complex multi-step tasks on your behalf.
Modern JavaScript in Practice
Move beyond basic syntax to build high-performance, interactive web components. Learn the professional patterns used to manage state, handle asynchronous data, and manipulate the DOM with precision.
Start The Architecture of Intelligence today.
Download Tomo, search The Architecture of Intelligence, and play your first lesson in under a minute.