Anthropic's Claude Cowork Is an AI Agent That Actually Works Cowork is a user-friendly version of Anthropic's Claude Code AI-powered tool that's built for file management and basic computing tasks. Here's what it's like to use it. As a software reporter at WIRED, I've tested a lot of shitty agents over the past couple of years. These experiences expose a consistent pattern of generative AI startups overpromising and underdelivering when it comes to these "agentic" helpers--programs designed to take control of your computer, performing chores and digital errands to free up your time for more important things. But the bots I installed on my laptop would struggle to complete even basic tasks.

Breakthroughs, discoveries, and DIY tips sent every weekday. Sinking feelings don't come much worse than when you think you delete something you really need. Many of us now have files synced to the cloud from our phones and laptops, but sometimes data can disappear from there too--maybe through a click of the wrong button or a swipe across the wrong menu option. If this happens to you, don't lose hope-most cloud storage services come with a deleted file restore function that's similar to the Recycle Bin on Windows and the Trash folder on macOS. It means that any files that you delete, deliberately or not, can be recovered without too much fuss.

Microsoft updated its Windows 11 support documentation to clarify that AI agents now require explicit user permission to access six key folders: Documents, Downloads, Desktop, Music, Pictures, and Videos. PCWorld reports that users can manage these permissions through Windows 11 Settings under System > AI Components > Agents, with options including'Allow Always,' 'Ask Every Time,' and'Never Allow.' The permission settings apply collectively to all six folders rather than individually, giving users control over AI agent access to their personal files. Back in October, Microsoft released a new support page for Experimental Agentic Features, which details how AI agents and agent connectors work with Windows 11, Copilot, etc. Recently, that page was updated to say that AI agents would be able to access the contents of six select folders in Windows 11--Documents, Downloads, Desktop, Music, Pictures, Videos--which understandably raised concerns. Now, Microsoft clarifies that you'll need to give your permission for AI agents to access the contents of those six folders. When selecting permissions, you'll have options for "Allow Always" (the agent can access these folders whenever it needs to), "Ask Every Time" (you'll be prompted when the agent needs access to the folders), and "Never Allow" (the agent will be denied the request every time). Note that it isn't possible to allow individual access settings per folder. The setting applies to all six folders or none of them.

Discovering which tables in large, heterogeneous repositories can be joined and by what transformations is a central challenge in data integration and data discovery. Traditional join discovery methods are largely designed for equi-joins, which assume that join keys match exactly or nearly so. These techniques, while efficient in clean, well-normalized databases, fail in open or federated settings where identifiers are inconsistently formatted, embedded, or split across multiple columns. Approximate or fuzzy joins alleviate minor string variations but cannot capture systematic transformations. We introduce QJoin, a reinforcement-learning framework that learns and reuses transformation strategies across join tasks. QJoin trains an agent under a uniqueness-aware reward that balances similarity with key distinctiveness, enabling it to explore concise, high-value transformation chains. To accelerate new joins, we introduce two reuse mechanisms: (i) agent transfer, which initializes new policies from pretrained agents, and (ii) transformation reuse, which caches successful operator sequences for similar column clusters. On the AutoJoin Web benchmark (31 table pairs), QJoin achieves an average F1-score of 91.0%. For 19,990 join tasks in NYC+Chicago open datasets, Qjoin reduces runtime by up to 7.4% (13,747 s) by using reusing. These results demonstrate that transformation learning and reuse can make join discovery both more accurate and more efficient.

All you need is a free app and your phone. Breakthroughs, discoveries, and DIY tips sent every weekday. If your home office is piled up high with papers, getting these documents digitized isn't as daunting a task as you might have thought. You don't need a big flatbed scanner or expensive software: All you need is your smartphone and Google Drive for Android or iOS . Load up Google Drive, point your phone's camera at a document, and you can turn it into a PDF that can be safely stored in the cloud--and which can be sorted and searched through like any other file in Google Drive.

Has Your Pledge to Go Paperless Perished? You promised yourself you'd digitize every last receipt, document, and paper record. But the trick to getting rid of paper is to not worry about being perfect. Wanting to get rid of paper in your life is easy. Following through with that promise to yourself is hard.

Apple has retired the Mac's Launchpad, a feature that displayed all your apps and let you quickly pick the one you want to open. You can recreate the app launcher using these alternatives. The latest version of macOS, named Tahoe, added all kinds of new features to the Mac desktop. It also removed one: Launchpad. The feature, which gave Mac users an iPhone-like grid of applications complete with support for folders, is missing from macOS 26.

It's important to monitor road issues such as bumps and potholes to enhance safety and improve road conditions. Smartphones are equipped with various built - in sensors that offer a cost - effective and straightforward way to assess road quality. However, prog ress in this area has been slow due to the lack of high - quality, standardized datasets. This paper discusses a new dataset created by a mobile app that collects sensor data from devices like GPS, accelerometers, gyroscopes, magnetometers, gravity sensors, and orientation sensors. This dataset is one of the few that integrates Geographic Information System (GIS) data with weather information and video footage of road conditions, providing a comprehensive understanding of road issues with geographic context . The dataset allows for a clearer analysis of road conditions by compiling essential data, including vehicle speed, acceleration, rotation rates, and magnetic field intensity, along with the visual and spatial context provided by GIS, weather, and video dat a. Its goal is to provide funding for initiatives that enhance traffic management, infrastructure development, road safety, and urban planning . Additionally, the dataset will be publicly accessible to promote further research and innovation in smart transp ortation systems.

Large Language Models (LLMs) are adept at generating responses based on information within their context. While this ability is useful for interacting with structured data like code files, another popular method, Retrieval-Augmented Generation (RAG), retrieves relevant documents to augment the model's in-context learning. However, it is not well-explored how to best represent this retrieved knowledge for generating responses on structured data, particularly hierarchical structures like trees. In this work, we propose a novel bottom-up method to linearize knowledge from tree-like structures (like a GitHub repository) by generating implicit, aggregated summaries at each hierarchical level. This approach enables the knowledge to be stored in a knowledge base and used directly with RAG. We then compare our method to using RAG on raw, unstructured code, evaluating the accuracy and quality of the generated responses. Our results show that while response quality is comparable across both methods, our approach generates over 68% fewer documents in the retriever, a significant gain in efficiency. This finding suggests that leveraging implicit, linearized knowledge may be a highly effective and scalable strategy for handling complex, hierarchical data structures.