Active learning methods have shown great promise in reducing the number of samples necessary for learning. As automated learning systems are adopted into real-time, real-world decision-making pipelines, it is increasingly important that such algorithms are designed with safety in mind. In this work we investigate the complexity of learning the best safe decision in interactive environments. We reduce this problem to a safe linear bandits problem, where our goal is to find the best arm satisfying certain (unknown) safety constraints. We propose an adaptive experimental design-based algorithm, which we show efficiently trades off between the difficulty of showing an arm is unsafe vs suboptimal.

Barbie is one of the most successful children's toys in history, spawning a multimedia franchise that includes merchandise, video games and a live-action film. Since US toy giant Mattel launched the original Barbie in 1959, more than 1 billion of the dolls have been sold worldwide. Certainly, Barbie's looks have been tweaked over the years to reflect changing beauty ideals and societal shifts. But according to a new study, one subtle change to Barbie has gone largely unnoticed – until now. Scientists in Australia have found that Barbies today have flatter feet than they did in past decades.

A confession: This dispatch will not be coming to you from one of the long-devout Martha Wells faithful. I'm a convert, a curious reader who turned to Wells' The Murderbot Diaries series after reading my colleague Meghan Herbst's fantastic 2024 profile of the author, which left me questioning who would be challenged with taking on the series' title character in Apple TV's adaptation and why it was Alexander Skarsgård. Put differently, I wanted to know if the actor known for playing blood-sucker Eric Northman in True Blood and a berserker prince in The Northman would be the right fit to play a security robot, or SecUnit, struggling with social awkwardness after hacking his own "governor module" to give himself the freedom to not obey human orders. If the weird affection he forms for the scientists he's charged with protecting, and the stunted way he goes about showing it, would translate to Murderbot. After watching the first episodes of the show, which debuts Friday on Apple TV, I got my answers--and found myself asking a lot more questions.

Artificial intelligence can spontaneously develop human-like social conventions, a study has found. The research, undertaken in collaboration between City St George's, University of London and the IT University of Copenhagen, suggests that when large language model (LLM) AI agents such as ChatGPT communicate in groups without outside involvement they can begin to adopt linguistic forms and social norms the same way that humans do when they socialise. The study's lead author, Ariel Flint Ashery, a doctoral researcher at City St George's, said the group's work went against the majority of research done into AI, as it treated AI as a social rather than solitary entity. "Most research so far has treated LLMs in isolation but real-world AI systems will increasingly involve many interacting agents," said Ashery. "We wanted to know: can these models coordinate their behaviour by forming conventions, the building blocks of a society? The answer is yes, and what they do together can't be reduced to what they do alone."

The UK government's proposed AI-powered crime prediction tool, designed to flag individuals deemed "high risk" for future violence based on personal data like mental health history and addiction, marks a provocative new frontier. Elsewhere, Argentina's new Artifical Intelligence Unit for Security intends to use machine learning for crime prediction and real-time surveillance. And in some US cities, AI facial recognition is paired with street surveillance to track suspects. The promise of anticipating violence Minority Report-style is compelling.

Feedback is New Scientist's popular sideways look at the latest science and technology news. You can submit items you believe may amuse readers to Feedback by emailing feedback@newscientist.com Saturday 17 May will see the final of this year's Eurovision Song Contest, which will be the most over-the-top evening of television since, well, the previous Eurovision. Feedback is deeply relieved that Feedback Jr appears not to be interested this year, so we might escape having to sit up and watch the entire thing. While we are deeply supportive of the contest's kind and welcoming vibe, most of the songs make our ears bleed.

Breakthroughs, discoveries, and DIY tips sent every weekday. Poison dart frogs are hard to miss. They're bright, agile, and as their name suggests, toxic. But at least a few of these showy amphibians have gone under the radar, until now. Scientists surveying a difficult to reach area of the Brazilian Amazon report two new species in a set of recent papers. The first, published in April in the journal ZooKeys, describes the teal and black Ranitomeya aquamarina.

The problem with the UK, according to the former Google boss Eric Schmidt, is that it has "so many ways that people can say no". However, for some critics of the Labour government, it has a glaring issue with saying yes: to big tech. Schmidt made his comment in a Q&A conversation with Keir Starmer at a big investment summit in October last year. The prominent position of a tech bigwig at the event underlined the importance of the sector to a government that has made growth a priority and believes the sector is crucial to achieving it. Top US tech firms have a big presence in the UK, including Google, Mark Zuckerberg's Meta, Amazon, Apple, Microsoft and Palantir, the data intelligence firm co-founded by the Maga movement backer Peter Thiel.

It is an instance of a key structural condition that applies across broad domains of machine learning. In particular, the assumption of low-rank feature representations led to algorithmic developments in many architectures. For neural networks, however, the intrinsic mechanism that yields low-rank structures remains vague and unclear. To fill this gap, we perform a rigorous study on the behavior of network rank, focusing particularly on the notion of rank deficiency. We theoretically establish a universal monotone decreasing property of network ranks from the basic rules of differential and algebraic composition, and uncover rank deficiency of network blocks and deep function coupling.

Model-based reinforcement learning agents must make compromises about which aspects of the environment their models should capture. The value equivalence (VE) principle posits that these compromises should be made considering the model's eventual use in value-based planning. Given sets of functions and policies, a model is said to be order- k VE to the environment if k applications of the Bellman operators induced by the policies produce the correct result when applied to the functions. Prior work investigated the classes of models induced by VE when we vary k and the sets of policies and functions. This gives rise to a rich collection of topological relationships and conditions under which VE models are optimal for planning.