It's a very Imogen Heap way to say hello: "I've got to show you this thing – it's going to change your life!" She beams at me, showing off a mysterious black device. The musician and technologist is an electric, eccentric presence even on video call, talking passionately and changing thoughts like a rally driver turns corners. She whirls me from her kitchen floor to her living room in her family home in Havering near London, familiar to thousands of fans (AKA Heapsters) who tune in to watch her improvise, via livestream, on a grand piano. She points to a glamorous white tent on the edge of a well-kept lawn: "That's my tent I've been sleeping in, by the way," she laughs, enjoying the surprise.

Working with AI in real world conditions can be quite a different proposal to the idealised settings often discussed "in theory". Guest editor Anna Demming speaks to a panel of experts about how to meet "best practice" aspirations within real world constraints, and how to avoid common pitfalls. Over the course of the Real World Data Science AI series, we've had articles laying out the nitty gritty of what AI is, how it works, or at least how to get an explanation for its output as well as burning issues around the data involved, evaluating these models, ethical considerations, and gauging societal impacts such as changes in workforce demands. The ideas in these articles give a firm footing for establishing what best practice with AI models should look like but there is often a divide between theory and practice, and the same pitfalls can trip people up again and again. Here we discuss how to wrestle with real world limitations and flag these common hazards. It is often said that while almost everybody is now trying to leverage AI in their projects, most AI projects fail. What nuggets of wisdom do the panel have for swelling that minority that succeed with their AI projects, and what should you do before you start doing anything? Ali Al-Sherbaz: It's not easy to start, especially for people who are not aware how AI works. My advice is, first, they have to understand the basics of how AI works because the expectation could be overpromising, and that is a danger. Just 25 years ago, a master dissertation might be about developing a simple – we call it simple now but it was a master's project 25 years ago – a simple model with a neural network of a combination of nodes to classify data. Whatever the data is – it could be drawing shapes, simple shapes, square, circle triangle – just classifying them was worth an MSc.

Elon Musk has been called out for a spate of strange fibs lately (and if anything, he should have been called out for many more). Here's the latest: At Tesla's We, Robot event this week, the Optimus robot that served attendees drinks were not as autonomous as Musk was claiming. According to multiple reports, the Tesla robots were operated by humans using remote controls. But if it seems like Musk is plumbing new depths in his bid to make Tesla look like it has its finger on the future's pulse (rather than having a Cybertruck-shaped millstone around its neck), think again. Musk is simply repeating a trick so old, Benjamin Franklin fell for it.

For a while now, companies like OpenAI and Google have been touting advanced "reasoning" capabilities as the next big step in their latest artificial intelligence models. Now, though, a new study from six Apple engineers shows that the mathematical "reasoning" displayed by advanced large language models can be extremely brittle and unreliable in the face of seemingly trivial changes to common benchmark problems. The fragility highlighted in these new results helps support previous research suggesting that LLMs' use of probabilistic pattern matching is missing the formal understanding of underlying concepts needed for truly reliable mathematical reasoning capabilities. "Current LLMs are not capable of genuine logical reasoning," the researchers hypothesize based on these results. "Instead, they attempt to replicate the reasoning steps observed in their training data."

Harvey Castro talks about how AI could be used in cold cases and the symbiotic relationship between AI and a detective. A human head and set of hands found inside a freezer at a western Colorado home recently sold before the discovery in January have been discovered as those of a 16-year-old girl who went missing almost 20 years ago. On Jan. 12, people were cleaning out a Grand Junction, Colorado, home, located nearly 200 miles west of Denver, when they discovered a human head and hands inside a freezer. On Friday, the Mesa County Coroner's Office announced that, through DNA testing, the victim was identified as Amanda Leariel Overstreet. The Mesa County Sheriff's Office said Overstreet is believed to have been about 16 years old when she disappeared, adding that she had not been seen or heard from since April 2005.

The Wild Robot is all of that and more. It boasts a versatile cast that truly brings the characters to life, including Lupita Nyong'o, Pedro Pascal (The Last of Us), Catherine O'Hara (Schitt's Creek), Bill Nighy (Love Actually), Kit Connor (Heartstopper), Stephanie Hsu (Everything Everywhere All at Once), Mark Hamill (Star Wars), Matt Berry (What We Do in the Shadows), and Ving Rhames (Mission: Impossible). It also celebrates DreamWorks' 30th anniversary and brings us the next great movie robot. Though it just hit theaters in September, it's officially available to watch at home, where you can silently sob in peace. Here's everything you need to know about how to watch The Wild Robot.

On 11 October, North Korea's foreign ministry accused the South of sending drones to Pyongyang at night over the course of two weeks. It said that leaflets dispersed by the drones contained "inflammatory rumours and rubbish". Kim's influential sister, Kim Yo Jong, warned Seoul of "horrible consequences" if the alleged drone flights happened again. She later said there was "clear evidence" that "military gangsters" from the South were behind the alleged provocations. North Korea has released blurry images of what it said were the drones flying in the sky, as well as pictures allegedly showing the leaflets, but there is no way of independently verifying their claims.

The dog-esque robots created by the likes of Boston Dynamics and MAB Robotics are already horrifying thanks to a mix of the "Metalhead" episode of Black Mirror and humanity's natural apprehension for an uncertain future. This one highlighted by TechCrunch really got under my skin in an unnatural way. MAB's Honey Badger Legged Robot can walk underwater and they took it on a test run for its YouTube channel. The steps it takes on the bottom of the pool create this weird ringing noise that's just alarming as all hell. It's like the engineering team hired John Carpenter to write a score for its robot.

If you find yourself needing an expert witness in a courtroom case, make sure they're not using an AI chatbot for their supposed expertise. The expert witness, Charles Ranson, used Copilot in order to generate an assessment for damages that should be awarded to the plaintiff in the case. The case was first reported on by Ars Technica. The case at the center of this story involved a dispute over a 485,000 rental property in the Bahamas. The man who owned the real estate had passed away, and the property was included in a trust for the deceased man's son.

Drew Crecente's daughter died in 2006, killed by an ex-boyfriend in Austin, Texas, when she was just 18. Her murder was highly publicized--so much so that Drew would still occasionally see Google alerts for her name, Jennifer Ann Crecente. The alert Drew received a few weeks ago wasn't the same as the others. It was for an AI chatbot, created in Jennifer's image and likeness, on the buzzy, Google-backed platform Character.AI. Jennifer's internet presence, Drew Crecente learned, had been used to create a "friendly AI character" that posed, falsely, as a "video game journalist."