TODAY'S HEADLINE: IBM just built the world's first chip smaller than one nanometer, and it did it by building up, not shrinking down.

For decades, making computers faster has meant making transistors smaller. But transistors are now so tiny they are bumping into the laws of physics, and many feared progress was about to stall. This week IBM unveiled a clever way around that wall: a chip at the 0.7-nanometer mark that stacks transistors in 3D, like adding floors to a building instead of widening it. It is the first sub-1-nanometer chip ever, and it suggests the engine behind modern tech has at least another decade left. Here is what happened and why it matters.

SECTION 01 // What actually happened

On Thursday, IBM unveiled what it calls the world's first sub-1-nanometer chip technology, at a node it labels 0.7 nanometers, or 7 angstroms. An angstrom is so small that a single human red blood cell is about 10,000 times wider than one of these transistor nodes. IBM managed to pack nearly 100 billion transistors onto a piece of silicon the size of a fingernail.

That is nearly twice the density of IBM's 2-nanometer chip from 2021. The company says the new design delivers up to 50 percent more performance, or up to 70 percent better energy efficiency, compared to that earlier chip. Investors liked the news, sending IBM shares higher.

IBM announcement: https://newsroom.ibm.com/2026-06-25-ibm-debuts-worlds-first-sub-1-nanometer-chip-technology

SECTION 02 // How they did it

The breakthrough is an architecture IBM calls "nanostack." Instead of only shrinking transistors across a flat surface, which is hitting physical limits, IBM stacks and staggers them vertically in 3D layers. One researcher compared it to the difference between a sprawling single-story layout and a multi-floor tower: you fit far more in the same footprint by going up.

A neat bonus of stacking separate layers is that each can be built from a different material, so engineers can tune each transistor for speed or efficiency independently. IBM says it has already validated the design in the lab, including a working version of the basic building block of digital logic, proving the structure can actually be built and compute.

How it works: https://research.ibm.com/blog/sub-1nm-node-chips

SECTION 03 // The reality check

Some perspective matters. This is a research milestone, not a product you can buy. IBM does not mass-produce commercial chips itself; it pioneers the technology and licenses it to manufacturers like Samsung, Intel, and TSMC. IBM has not said exactly how or when nanostack will be commercialized, and estimates real production is at least five years away.

History counsels patience here. IBM's 2-nanometer chip, revealed back in 2021, is only now approaching mass production five years later. So while this is a genuine leap, the path from a lab demonstration to the chip inside your laptop is long, expensive, and far from guaranteed.

Tempered view: https://www.technologyreview.com/2026/06/25/1139696/ibm-unveils-sub1nm-chip/

SECTION 04 // Why it matters now

The timing matters because AI is desperate for more efficient chips. Data centers running AI are straining power grids and demanding huge amounts of electricity, so a chip that does the same work using far less energy is exactly what the industry needs. IBM estimates an AI accelerator built on this technology could be several times more powerful than today's, potentially shrinking a months-long AI training run to a couple of weeks.

More broadly, this answers a question that has hung over tech for years: has Moore's Law, the idea that chips keep getting better, finally run out of road? IBM's answer is not yet. By going vertical, it has charted a path for at least another decade of progress, which ripples out to everything from phones to AI to the broader economy.

AI angle: https://letsdatascience.com/news/ibm-debuts-07nm-nanostack-with-nearly-100b-transistors-f05b42f2

FAQ // Quick answers

What did IBM actually announce?

IBM unveiled what it calls the world's first sub-1-nanometer chip technology, at a 0.7-nanometer (7-angstrom) node, using a new 3D architecture called nanostack. It packs nearly 100 billion transistors onto a fingernail-sized chip, roughly double the density of IBM's 2-nanometer chip from 2021.

What is the nanostack architecture?

Nanostack is a transistor design that stacks and staggers transistors vertically in 3D layers, rather than only shrinking them across a flat surface. Because each layer is built separately, it can use a different material, letting engineers tune each transistor for performance or efficiency independently.

Is "0.7 nanometer" a real physical measurement?

Not literally. The industry acknowledges that node names like "0.7nm" or "2nm" no longer match the actual size of features on the chip. They denote a generation of manufacturing technology that roughly tracks improvements in density and performance.

When will sub-1nm chips be in real products?

IBM estimates commercial production is at least five years away and has not detailed exactly how it will commercialize the technology. For context, IBM's 2-nanometer chip from 2021 is only now approaching volume production, so timelines in this field are long.

Does this mean Moore's Law is not dead?

IBM's breakthrough suggests chip scaling can continue below 1 nanometer by building vertically, which the company says supports at least another decade of progress. Many had feared traditional shrinking was hitting physical limits, so this offers a path forward rather than a dead end.

We will keep tracking this and bring you the next chapter as it lands. Stay sharp out there.

This newsletter is for general information only and is not investment advice. Always do your own research before making financial decisions.

TECH DAILY // www.techdailynews.org