Realistic drawing of a printed circuit board, with circuit lines projecting above it in the shape of a brain

Machine-learning System Based on Light Could Yield More Powerful, Efficient Large Language Models

Elizabeth A. Thomson | Materials Research Laboratory

MIT system demonstrates greater than 100-fold improvement in energy efficiency and a 25-fold improvement in compute density compared with current systems.

A streak of blue lightning, representing energy, spreads horizontally across a textured cement surface.

MIT Engineers Create an Energy-storing Supercapacitor from Ancient Materials

David L. Chandler | MIT News

Made of cement, carbon black, and water, the device could provide cheap and scalable energy storage for renewable energy sources.

leaf and forest viewed through a round window like lense surrounded by green abstract cyber computer chip patterns

Shivam Kajale of Nano-Cybernetic Biotrek Creates Awareness About the Urgent Need to Develop Environmentally Sustainable AI

Mark Grinstein-Camacho

The impending threat of large-scale computation to the environment often goes unnoticed in our software-orientated world.

Futuristic central processor unit. Powerful Quantum CPU on PCB motherboard with data transfers.

A New Chip for Decoding Data Transmissions Demonstrates Record-breaking Energy Efficiency

Adam Zewe | MIT News Office

The chip, which can decipher any encoded signal, could enable lower-cost devices that perform better while requiring less hardware.

An image of a yellow and pink car with dissolved edges is shown with a blue background.

Computers that Power Self-driving Cars Could be a Huge Driver of Global Carbon Emissions

Adam Zewe | MIT News Office

Study shows that if autonomous vehicles are widely adopted, hardware efficiency will need to advance rapidly to keep computing-related emissions in check.

male scientist is bending to look inside window of large silver scientific machinery

Putting a New Spin on Computer Hardware

Adam Zewe | MIT News Office

Luqiao Liu utilizes a quantum property known as electron spin to build low-power, high-performance computer memories and programmable computer chips.

computer chip containing many aligned squares

Computing With Chemicals Makes Faster, Leaner AI

Dina Genkina | IEEE Spectrum

Battery-inspired artificial synapses are gaining ground, and analog electrochemical memory (ECRAM) arrays provide a prototype for artificial synapses in AI training.

abstract multi color streaks of light sweeping upward to show fast movement

Breaking the Scaling Limits of Analog Computing

Adam Zewe | MIT News Office

MIT researchers have developed a new technique could diminish errors that hamper the performance of super-fast analog optical neural networks.

rendering of a novel piece of hardware, called a smart transceiver, that uses silicon photonics to dramatically accelerate running a machine-learning model

Deep Learning with Light

Adam Zewe | MIT News Office

A new novel piece of hardware, called a smart transceiver, uses silicon photonics to accelerate machine-learning computations on smart speakers and other low-power connected devices.

Hydrogen molecule graphic

3 Questions: Blue Hydrogen and the World’s Energy Systems

Turner Jackson | MIT Energy Initiative

Research Scientist Emre Gençer describes natural gas–based hydrogen production with carbon capture and storage, and the role hydrogen will play in decarbonizing our energy systems.