Skip to main content

Moore’s Law back on track with IBM carbon nanotube breakthrough

IBM has discovered a way to make computer processors that are faster and even more power efficient, allowing it to keep up with Moore’s Law for least the next several years. The breakthrough, revealed on Thursday, describes a way of bonding molybdenum to a carbon nanotube in order to create a contact point for a circuit. This process will allow IBM to replace silicon transistors with carbon nanotubes in future chipset designs.

For those of you who might not be familiar, Moore’s Law is a fifty-year-old idea conceived by Gordon Moore, co-founder of Intel. It says the number of transistors on a computer chip will double every 18 months — and has held true over the past half century. For the semiconductor industry, more transistors translates into faster processors, a scenario that has driven the computing industry and paved the way for our current crop of smartphones and smart watches.

Recommended Videos

Today, companies build their chips using silicon, which is reaching its material limits. As a result, Moore’s Law has slowed down, causing tech pundits the world over to predict the end of the “smaller, faster, cheaper” era of processing tehcnology. Even Intel CEO Brian Krzanich said during a recent earnings conference call that company would not be able to keep up with the pace set by Moore’s Law.

Please enable Javascript to view this content

IBM’s breakthrough, which was published this week in Science, describes a way of building transistors with carbon nanotubes instead of silicon. Carbon-based nanotubes are a 10,000 times smaller than a human hair and conduct electricity, making them ideal for their role in semiconductor manufacturing. These new carbon nanotubes theoretically allow engineers to build chips with transistors that are 3-5 nanometers apart, as compared to the 11-14 nanometers present in the current crop of advanced chips.

This potentially is a game-changing discovery, providing reassurance that there will be semiconductors that can advance beyond the limitations set by silicon. In other words, Moore’s Law can continue on. For awhile, anyway.

Kelly Hodgkins
Kelly's been writing online for ten years, working at Gizmodo, TUAW, and BGR among others. Living near the White Mountains of…
Nvidia might once again delay the GPU gamers want most
Two RTX 4060 graphics cards stacked on top of each other.

If a GPU is yet to be announced, can we consider it to be delayed? Maybe, maybe not, but if you trust leakers, Nvidia's upcoming best graphics cards for gamers on a budget are seemingly stuck in limbo. The RTX 5060 and the RTX 5060 Ti are said to be delayed once again, and gamers might have to wait for quite a long time to get their hands on one of the new RTX 50-series GPUs.

This grim update comes from Board Channels, which is a website frequented by people who claim to be affiliated with Nvidia's add-in board (AIB) partners. According to the report, the RTX 5060 Ti (in both its iterations, meaning the 8GB and the 16GB models) will now launch in mid-April, followed by the RTX 5060 in mid-May. Nvidia is said to have notified its AIBs about these delays.

Read more
NotebookLM’s new Mind Maps could help you learn more efficiently
Google video of NotebookLM mind map feature.

NotebookLM users have a few new features to play around with starting this week, including a visual summary feature dubbed "Mind Map."

For anyone who isn't familiar with NotebookLM, it's an AI tool from Google designed specifically for summarizing, searching, and analyzing libraries of information. The idea is that you provide it with a selection of documents and files, and it will help you interact with them using natural language.

Read more
Watch a robot dog learn to stand and walk thanks to its ‘digital brain’
intuicell robot dog 1 2

Move over, Boston Dynamics, as there's a new robot dog in town. Swedish startup IntuiCell has unveiled its AI model that learns and adapts to its environment, demonstrated through a robot dog named Luna.

While most traditional animal-like robots have been trained on specific movements using machine learning that they can then execute, IntuiCell has a different approach: an AI agent that educates itself autonomously. The company calls the concept a "digital nervous system," as it mimics a biological nervous system and allows the robot to experiment, process, and adapt its interactions with the world.

Read more