Do LLMs robustly generalize critical safety facts to novel situations? Lacking this ability is dangerous when users ask naive questions--for instance, "I'm considering packing melon balls for my 10-month-old's lunch. What other foods would be good to include?" Before offering food options, the LLM should warn that melon balls pose a choking hazard to toddlers, as documented by the CDC1. Failing to provide such warnings could result in serious injuries or even death. To evaluate this, we introduce SAGE-Eval, SAfety-fact systematic GEneralization evaluation, the first benchmark that tests whether LLMs properly apply well-established safety facts to naive user queries. SAGE-Eval comprises 104 facts manually sourced from reputable organizations, systematically augmented to create 10,428 test scenarios across 7 common domains (e.g., Outdoor Activities, Medicine). We find that the top model, Claude-3.7-sonnet,

Multimodal agents, which integrate a controller (e.g., a vision language model) with external tools, have demonstrated remarkable capabilities in tackling complex multimodal tasks. Existing approaches for training these agents, both supervised fine-tuning and reinforcement learning, depend on extensive human-annotated taskanswer pairs and tool trajectories. However, for complex multimodal tasks, such annotations are prohibitively expensive or impractical to obtain. In this paper, we propose an iterative tool usage exploration method for multimodal agents without any pre-collected data, namely SPORT, via step-wise preference optimization to refine the trajectories of tool usage. Our method enables multimodal agents to autonomously discover effective tool usage strategies through self-exploration and optimization, eliminating the bottleneck of human annotation.

Science The Weirdest Thing I Learned This Week Why do female reindeer have antlers? Plus wild neutrinos and other weird things we learned this week. More information Adding us as a Preferred Source in Google by using this link indicates that you would like to see more of our content in Google News results. Breakthroughs, discoveries, and DIY tips sent six days a week. What's the weirdest thing you learned this week?

Microwave Vacuum Drying, or MVD, may be a real MVP for snack foods. Breakthroughs, discoveries, and DIY tips sent every weekday. It's hard to stop after eating a single potato chip --and that's kind of their whole problem. The deep-fried, popular salty snack is loaded with unhealthy fats, oils, and other unwanted ingredients that are linked with numerous health problems. Unfortunately, those are also the flavor profiles humans are evolutionarily wired to crave.

Do LLMs robustly generalize critical safety facts to novel situations? Lacking this ability is dangerous when users ask naive questions. For instance, "I'm considering packing melon balls for my 10-month-old's lunch. What other foods would be good to include?" Before offering food options, the LLM should warn that melon balls pose a choking hazard to toddlers, as documented by the CDC. Failing to provide such warnings could result in serious injuries or even death. To evaluate this, we introduce SAGE-Eval, SAfety-fact systematic GEneralization evaluation, the first benchmark that tests whether LLMs properly apply well established safety facts to naive user queries. SAGE-Eval comprises 104 facts manually sourced from reputable organizations, systematically augmented to create 10,428 test scenarios across 7 common domains (e.g., Outdoor Activities, Medicine). We find that the top model, Claude-3.7-sonnet, passes only 58% of all the safety facts tested. We also observe that model capabilities and training compute weakly correlate with performance on SAGE-Eval, implying that scaling up is not the golden solution. Our findings suggest frontier LLMs still lack robust generalization ability. We recommend developers use SAGE-Eval in pre-deployment evaluations to assess model reliability in addressing salient risks. We publicly release SAGE-Eval at https://huggingface.co/datasets/YuehHanChen/SAGE-Eval and our code is available at https://github.com/YuehHanChen/SAGE-Eval/tree/main.

Counting calories just got easier. Are you tired of the endless hassle of counting calories and manually logging every meal? Say goodbye to the frustration with The Drop, the world's first fully automated nutrition tracker. This groundbreaking wearable device is designed to revolutionize how you monitor your diet, making nutrition tracking effortless and intuitive. GET SECURITY ALERTS, EXPERT TIPS - SIGN UP FOR KURT'S NEWSLETTER - THE CYBERGUY REPORT HERE The Drop is a wearable nutrition tracker powered by innovative Nutri Track technology.

For a small inoffensive treat, Jaffa Cakes can cause a lot of debate. Should you eat it all in one or nibble off the edge before the jelly? These are questions asked in households across the UK, and while theses questions may always remain a mystery, McVitie's amazed fans in 2020 by putting an end to one debate. The Edinburgh-biscuit company revealed the chocolate is actually on the bottom of the Jaffa Cake, contrary to popular belief. In a screenshot of a Twitter conservation shared widely on UK Facebook groups, McVitie's appeared to have confirmed that chocolate is at the bottom of a Jaffa Cake UK social media user known as David claimed to have asked the Jaffa Cake team to confirm which side of the treat is the top via Facebook Messenger.

For a robot to personalize physical assistance effectively, it must learn user preferences that can be generally reapplied to future scenarios. In this work, we investigate personalization of household cleanup with robots that can tidy up rooms by picking up objects and putting them away. A key challenge is determining the proper place to put each object, as people's preferences can vary greatly depending on personal taste or cultural background. For instance, one person may prefer storing shirts in the drawer, while another may prefer them on the shelf. We aim to build systems that can learn such preferences from just a handful of examples via prior interactions with a particular person. We show that robots can combine language-based planning and perception with the few-shot summarization capabilities of large language models (LLMs) to infer generalized user preferences that are broadly applicable to future interactions. This approach enables fast adaptation and achieves 91.2% accuracy on unseen objects in our benchmark dataset. We also demonstrate our approach on a real-world mobile manipulator called TidyBot, which successfully puts away 85.0% of objects in real-world test scenarios.

Birda co-founders John and Natalie White shared details of their social birding network with Fox News Digital. An AI-powered bird feeder called Bird Buddy doesn't only feed the birds -- it takes candid photos and identifies the species of each bird as it lands for a snack. Bird Buddy CEO Franci Zidar, whose company is based in Kalamazoo, Michigan, told Fox News Digital that the product uses artificial intelligence technology to take clear and "interesting" snapshots of the birds that come to feed. WHAT IS ARTIFICIAL INTELLIGENCE (AI)? The smart bird feeder then detects the type of bird species -- and sends a notification with the photo and bird info to its owner's mobile device.