Researchers are figuring out how large language models work
Such insights could help make them safer, more truthful and easier to use
TO MOST PEOPLE, the inner workings of a car engine or a computer are a mystery. It might as well be a black box: never mind what goes on inside, as long as it works. Besides, the people who design and build such complex systems know how they work in great detail, and can diagnose and fix them when they go wrong. But that is not the case for large language models (LLMs), such as GPT-4, Claude and Gemini, which are at the forefront of the boom in artificial intelligence (AI).
Explore more
This article appeared in the Science & technology section of the print edition under the headline “Inside the mind of an AI”
From the July 13th 2024 edition
Discover stories from this section and more in the list of contents
Explore the editionMore from Science & technology
Why a new art gallery in Bangalore is important for Indian science
It aims to make research and tinkering more accessible to the public
Climate change could reawaken harmful invasive plants
The sooner they can be weeded out, the better
AI scientists are producing a host of new theories of how our brains learn
The challenge for neuroscientists is how to test them
Exposure to the sun’s UV radiation may be good for you
For now, though, keep the sun cream handy
Engineered dust could help make Mars habitable
Restoring water on Mars may be easier than you think
New batteries are stretchable enough to wear against the skin
They take their inspiration from electric eels