Anthropic's New Defense Against AI Jailbreaks and Rubin Observatory's Quest to Understand Dark Matter

The Download: understanding dark matter, and AI jailbreak protection

How the Rubin Observatory will help us understand dark matter and dark energy We can put a good figure on how much we know about the universe: 5%. That's how much of what's floating about in the cosmos is ordinary matter -- planets and stars and galaxies and the dust and gas between them. The other 95% is dark matter and dark energy, two mysterious entities aptly named for our inability to shed light on their true nature. Previous work has begun pulling apart these dueling forces, but dark matter and dark energy remain shrouded in a blanket of questions -- critically, what exactly are they? Enter the Vera C. Rubin Observatory, one of our 10 breakthrough technologies for 2025. Boasting the largest digital camera ever created, Rubin is expected to study the cosmos in the highest resolution yet once it begins observations later this year. And with a better window on the cosmic battle between dark matter and dark energy, Rubin might narrow down existing theories on what they are made of. Here's a look at how. -- Jenna Ahart This story is part of MIT Technology Review Explains, our series untangling the complex, messy world of technology to help you understand what's coming next. You can read more from the series here. Anthropic has a new way to protect large language models against jailbreaks What's new? AI firm Anthropic has developed a new line of defense against a common kind of attack called a jailbreak. A jailbreak tricks large language models (LLMs) into doing something they have been trained not to, such as help somebody create a weapon. And Anthropic's new approach could be the strongest shield against the attacks yet. How they did it: Jailbreaks are a kind of adversarial attack: input passed to a model that makes it produce an unexpected output. Despite a decade of research there is still no way to build a model that isn't vulnerable. But, instead of trying to fix its models, Anthropic has developed a barrier that stops attempted jailbreaks from getting through and unwanted responses from the model getting out. Read the full story.

The Download: understanding deep matter, and AI jailbreak protection

How the Rubin Observatory will help us understand dark matter and dark energy We can put a good figure on how much we know about the universe: 5%. That's how much of what's floating about in the cosmos is ordinary matter -- planets and stars and galaxies and the dust and gas between them. The other 95% is dark matter and dark energy, two mysterious entities aptly named for our inability to shed light on their true nature. Previous work has begun pulling apart these dueling forces, but dark matter and dark energy remain shrouded in a blanket of questions -- critically, what exactly are they? Enter the Vera C. Rubin Observatory, one of our 10 breakthrough technologies for 2025. Boasting the largest digital camera ever created, Rubin is expected to study the cosmos in the highest resolution yet once it begins observations later this year. And with a better window on the cosmic battle between dark matter and dark energy, Rubin might narrow down existing theories on what they are made of. Here's a look at how. -- Jenna Ahart This story is part of MIT Technology Review Explains, our series untangling the complex, messy world of technology to help you understand what's coming next. You can read more from the series here. Anthropic has a new way to protect large language models against jailbreaks What's new? AI firm Anthropic has developed a new line of defense against a common kind of attack called a jailbreak. A jailbreak tricks large language models (LLMs) into doing something they have been trained not to, such as help somebody create a weapon. And Anthropic's new approach could be the strongest shield against the attacks yet. How they did it: Jailbreaks are a kind of adversarial attack: input passed to a model that makes it produce an unexpected output. Despite a decade of research there is still no way to build a model that isn't vulnerable. But, instead of trying to fix its models, Anthropic has developed a barrier that stops attempted jailbreaks from getting through and unwanted responses from the model getting out. Read the full story.