Elaborate robberies are a Hollywood staple, and the real-life theft at the Louvre has become a phenomenon. Why are we riveted by this particular type of crime? On October 19th, a group of masked men broke into the Louvre in broad daylight and made off with some of France's crown jewels. Suspects are now in custody, but the online fervor is still going strong. On this episode of Critics at Large, Vinson Cunningham, Naomi Fry, and Alexandra Schwartz discuss the sordid satisfaction of watching a heist play out, both onscreen and off.

Thieves stole $100 million in jewels from the Louvre Museum in Paris after exploiting weak passwords, including using "Louvre" as a surveillance system password.

It's often more'smash and grab' than'Mission: Impossible.' French police officers stand next to a furniture elevator used by robbers to enter the Louvre Museum, on Quai Francois Mitterrand, in Paris on October 19, 2025. Robbers broke in to the Louvre and fled with jewellery on October 19, 2025 morning, a source close to the case said, adding that its value was still being evaluated. A police source said an unknown number of thieves arrived on a scooter armed with small chainsaws and used a goods lift to reach the room they were targeting. Breakthroughs, discoveries, and DIY tips sent every weekday. A heist at a world famous museum likely evokes images of stealthy cat burglars skulking at night armed with state-of-the-art gadgets, possibly even soundtracked with a cool, jazzy instrumental.

Understanding and manipulating the causal generation mechanisms in language models is essential for controlling their behavior. Previous work has primarily relied on techniques such as representation surgery -- e.g., model ablations or manipulation of linear subspaces tied to specific concepts -- to \emph{intervene} on these models. To understand the impact of interventions precisely, it is useful to examine counterfactuals -- e.g., how a given sentence would have appeared had it been generated by the model following a specific intervention. We highlight that counterfactual reasoning is conceptually distinct from interventions, as articulated in Pearl's causal hierarchy. Based on this observation, we propose a framework for generating true string counterfactuals by reformulating language models as a structural equation model using the Gumbel-max trick, which we called Gumbel counterfactual generation. This reformulation allows us to model the joint distribution over original strings and their counterfactuals resulting from the same instantiation of the sampling noise. We develop an algorithm based on hindsight Gumbel sampling that allows us to infer the latent noise variables and generate counterfactuals of observed strings. Our experiments demonstrate that the approach produces meaningful counterfactuals while at the same time showing that commonly used intervention techniques have considerable undesired side effects.

This article originally appeared in YFS Magazine. The art world has become a more inclusive, engaging place for newcomers and connoisseurs alike -- and we owe technology much of the credit. From machine learning and personalization to augmented reality and blockchain integrations, new technologies continue to reshape and reimagine what the art world can be and who has access to it. Many people still believe consumers won't buy art without experiencing it in-person. Online art galleries are flourishing, however, and new tools make it easier than ever for potential buyers to get up close and personal with works of art that could be thousands of miles away.

An artist has transformed the chipped stone busts of ancient Roman emperors into photorealistic portraits with the help of historical artefacts and creative software. Daniel Voshart, from Toronto, Canada, says that his project of painstakingly colourising and shaping the faces of 54 Principate rulers was'a quarantine project that got a bit out of hand', but it has attracted attention from hobbyists to historians. And he has now released his completed work in a series of stunning portraits and posters that cover 300 years of Roman history. Though more interested in design work for VR for use in architecture and the film industry, the coronavirus pandemic brought Daniel's work to stop and left him with time to explore his hobby of colourising statues. When he came to pick a subject however, he chose to research the busts of Roman Emperors who controlled its sprawling empire during the first three-century-long Principate, despite not being particularly interested in ancient history.

In 2012, I proposed the idea of creating a Global Language Archive. This was roughly the same time that the Endangered Languages Project was getting kicked off, which I'll discuss in more detail below. But I always viewed a Global Language Archive as being much more than an online effort. The world is losing languages at a rapid clip. Over 500 languages have less than 10 people still speaking them and many of these native speakers are losing the will to struggle forward to keep them viable.

Accenture has teamed up with a coder, an orchestral composer and a datavis company to put artificial intelligence (AI) and big data to music, in a project called Symphonologie. Looking to combine data with art, Symphonologie's visual music piece has three influences: business, technology and the new digital world. To combine all of these into one artistic experience, Accenture looked to Hannah Davis, a musician and creative technologist; Rare Volume, an interactive design and data company; and composer Mathieu Lamboley. The project began with Davis' thesis, which dealt with putting music to words. She built a computer programme called TransProse, which reads bodies of text and determines the "densities" of eight emotions: joy, sadness, anger, disgust, anticipation, surprise, trust, and fear.