Artificial Intelligence
Latest about Artificial Intelligence
MIT gives AI the power to 'reason like humans' by creating hybrid architecture
By Nicholas Fearn published
MIT scientists devise three abstraction libraries that can be combined with AI systems to improve their reasoning and contextual awareness in programming, strategic planning and robotics.
'It would be within its natural right to harm us to protect itself': How humans could be mistreating AI right now without even knowing it
By Keumars Afifi-Sabet published
How can we truly know if AI is sentient? We do not yet fully understand the nature of human consciousness, so we cannot discount the possibility that today's AI is indeed sentient — and that we are mistreating it to potentially grave consequences.
Claude 3 Opus has stunned AI researchers with its intellect and 'self-awareness' — does this mean it can think for itself?
By Roland Moore-Coyler published
Anthropic's AI tool has beaten GPT-4 in key metrics and has a few surprises up its sleeve — including pontificating about its existence and realizing when it was being tested.
Scientists create 'toxic AI' that is rewarded for thinking up the worst possible questions we could imagine
By Drew Turney published
Researchers at MIT are using AI to train AI not to give toxic responses, using a new method that replicates human curiosity.
Google builds an AI model that can predict future weather catastrophes
By Drew Turney published
A new system uses generative AI to predict weather faster and more cheaply than ever — while detecting difficult-to-spot extreme weather events — beating the world's major weather agencies.
What is artificial intelligence (AI)?
By Edd Gent published
This exciting field of computer science focuses on technologies that mimic human intelligence — with AI systems becoming way more prevalent in recent years.
'Jailbreaking' AI services like ChatGPT and Claude 3 Opus is much easier than you think
By Drew Turney published
AI researchers found they could dupe an AI chatbot into giving a potentially dangerous response to a question by feeding it a huge amount of data it learned from queries made mid-conversation.
MIT scientists have just figured out how to make the most popular AI image generators 30 times faster
By Keumars Afifi-Sabet published
Scientists have built a framework that gives generative AI systems like DALL·E 3 and Stable Diffusion a major boost by condensing them into smaller models — without compromising their quality.
Scientists create AI models that can talk to each other and pass on skills with limited human input
By Roland Moore-Coyler published
Scientists modeled human-like communication skills and the transfer of knowledge between AIs — so they can teach each other to perform tasks without a huge amount of training data.
Researchers gave AI an 'inner monologue' and it massively improved its performance
By Keumars Afifi-Sabet published
Scientists trained an AI system to think before speaking with a technique called QuietSTaR. The inner monologue improved common sense reasoning and doubled math performance.
Sign up for the Live Science daily newsletter now
Get the world’s most fascinating discoveries delivered straight to your inbox.