Chapter 1

Breaking free from the cloud

Chapter 2

The silicon inside your machine

Chapter 3

The open source brain trust

Chapter 4

Living with a local assistant

Ch 2 · The silicon inside your machine
007skaty

007skaty Apple's M1 chip uses unified memory to stop components from wasting speed copying data to themselves.

Oct 25

007skaty
Computers run local AI much faster when their internal chips share a single memory pool.

007skaty Unified memory breakthroughs eliminate system lag by allowing different processors to instantly access the exact same pool.

Oct 25

007skaty
A single silicon chip crosses over seventy borders before powering your local AI laptop.

007skaty A sleek modern laptop sits open on a wooden home table.

Oct 23

007skaty

007skaty Neural Processing Units

A grid of tiny circuits multiplies the math all day, To run your local chatbot on a systolic array.

Oct 25

007skaty
Fun Fact

Rise of NPUs: This dedicated silicon runs private AI locally, performing trillions of operations per second using less power than a standard LED lightbulb.

Hide sticker

Oct 29

007skaty
Gossip

Which NPU silicon is powering your local AI?

Oct 29

007skaty
Quiz

To run large private AI models locally on modern consumer devices, silicon designers utilize unified memory breakthroughs. What major performance bottleneck does unified memory solve compared to traditional computer architectures?

Oct 29

007skaty
Note

I Love You 💞

Hide sticker

Oct 23

007skaty

007skaty Apple's M1 chip in 2020 proved that sharing memory between processors removes the bottlenecks that slow down computers.

Oct 25

007skaty
Gaming graphics cards dominate local AI because this hardware handles thousands of calculations at once

007skaty The silicon inside your machine runs private AI on gaming hardware because these graphics cards multitask like nothing

Oct 24

007skaty

007skaty Global Semiconductor Supply Chain

Dutch light prints, Taiwan silicon, your AI thinks!

Oct 25

007skaty
Fun Fact

Rise of NPUs: This specialized silicon chip inside your machine runs private AI locally, performing trillions of tasks per second while using a fraction of your battery's power!

Hide sticker

Oct 23

007skaty
Gossip

Which global chip supply bottleneck is hurting your local AI setup most?

Oct 24

007skaty
Quiz

How do unified memory breakthroughs in modern computer silicon benefit devices running private AI models locally?

Oct 29

007skaty

007skaty The Compute Express Link standard allows everyday chips to share memory and perform like a single supercomputer.

Oct 23

007skaty
Silicon chips now feature dedicated hardware designed to process your private AI locally.

007skaty The rise of the NPU, a quiet third brain built inside our devices purely to run local artificial

Oct 24

007skaty

007skaty Unified Memory Breakthroughs

Zero-copy, zero-copy, CPU and GPU share the exact same space.

Oct 25

007skaty
Quiz

In computers designed to run private AI models locally, how does the breakthrough of unified memory architecture on modern silicon chips improve performance?

Oct 29

007skaty
Graphics cards rule AI because they handle thousands of calculations at once.

007skaty Graphics cards rule AI because they handle thousands of calculations at once.

Oct 23

007skaty

007skaty Global Chip Supply Chain

Seventy borders crossed / Twenty-five thousand miles / To run your machine

Oct 25

007skaty
Quiz

In modern personal computers designed to run private AI models locally, what is the primary purpose of the specialized Neural Processing Unit (NPU)?

Oct 29

007skaty

007skaty Graphics Cards for Local AI

Thousands of tiny cores doing math all at once

Oct 24

007skaty
Quiz

When setting up a computer to run a private AI model locally, why do graphics cards (GPUs) outshine standard central processing units (CPUs) at handling the workload?

Oct 29

007skaty

007skaty Neural Processing Unit

The silicon handles the AI math (oh yeah!) / Keeping it local on a low-power path (so quick!)

Oct 24

007skaty
Quiz

In computers designed to run private AI models locally, how do breakthroughs in unified memory architecture on modern silicon chips solve a major performance bottleneck?

Oct 29

007skaty

007skaty Global Chip Supply Chain

This chip crossed seventy borders (seventy borders!) To run your local AI (local AI!)

Oct 23

007skaty
Quiz

The silicon chips inside your computer that run private AI models locally require a highly complex global supply chain. While these advanced chips are often designed in the United States, they rely heavily on extreme ultraviolet (EUV) lithography machines—the only tools capable of printing their microscopic circuits—which are exclusively manufactured by a single company in which country?

Oct 29

007skaty

007skaty Graphics Cards

Thousands of cores, Solving all at once, Local logic flows!

Oct 23

007skaty
Quiz

While many tech companies design the advanced silicon chips needed to run private AI models locally, the global chip supply chain relies heavily on a single manufacturing foundry to fabricate almost all of these cutting-edge processors. Which company is this?

Oct 25

007skaty

007skaty Graphics Cards for AI

With thousands of cores working side by side, We multiply matrices to make the model glide

Oct 23

007skaty

007skaty Learn how Neural Processing Units (NPUs) enable computers to run private AI locally. Discover why NPUs are changing the future of personal computing.

Sep 4

007skaty
Quiz

What Dutch company is the sole manufacturer of the extreme ultraviolet (EUV) lithography machines needed to make advanced AI chips?

Sep 4

007skaty
Quiz

Which metric, measuring billions of operations per second, is used to rate NPU performance in modern AI PCs?

Sep 4

007skaty
My Tiny Thinker
BETA

007skaty Build your offline computer to learn how private AI runs without using the internet.

Sep 4

007skaty

007skaty Discover why GPUs are essential for running private AI locally. Learn how graphics cards power local artificial intelligence processing in this video.

Sep 4

007skaty
Why graphics cards rule AI

007skaty Graphics processing units, or GPUs, excel at AI because they can perform millions of mathematical calculations simultaneously instead of one by one.

Sep 4

007skaty
Quiz

Why are GPUs (Graphics Processing Units) preferred over traditional CPUs for running local AI?

Sep 4

007skaty
Quiz

What does the hardware acronym NPU stand for in modern computer processors?

Sep 4

007skaty

007skaty Silicon Processors

Refined from sand, this silicon code Runs private thoughts in offline mode.

Sep 4

007skaty

007skaty Watch how unified memory breakthroughs are transforming local hardware, allowing you to run private AI models directly on your computer.

Sep 4

007skaty
Unified memory breakthroughs

007skaty Unified memory architectures allow computers to share RAM dynamically between the processor and graphics card, making local AI run much faster.

Sep 4

007skaty
Quiz

What is the main physical side effect of running high-performance local AI models on a home computer?

Sep 4

007skaty
Quiz

Which Taiwanese company manufactures the vast majority of the world's advanced AI microchips?

Sep 4

007skaty
Fun Fact

GPU power: A single modern consumer graphics card contains more raw computing power than all the supercomputers in the world combined did in the mid-1990s.

Hide sticker

Sep 4

007skaty

007skaty Explore how the global chip supply chain affects the hardware needed to run private AI locally, including key production stages and bottlenecks.

Sep 4

007skaty
Quiz

Which type of computer memory is most critical for determining how large of an AI model you can run?

Sep 4

007skaty
Quiz

Which company revolutionized consumer local AI in 2020 by introducing unified memory in its M-series chips?

Sep 4

007skaty
Glossary
silicon (noun)
A chemical element used widely as a semiconductor in the manufacture of microchips and electronic circuits. Apple introduced its custom M1 silicon in 2020, enabling personal computers to process neural networks locally.
Hide sticker

Sep 4

007skaty
Gossip

Which hardware upgrade would you buy first?

Sep 4