Vehicle crashes involve complex interactions between road users, split-second decisions, and challenging environmental conditions. Among these, two-vehicle crashes are the most prevalent, accounting for approximately 70% of roadway crashes and posing a significant challenge to traffic safety. Identifying Driver Hazardous Action (DHA) is essential for understanding crash causation, yet the reliability of DHA data in large-scale databases is limited by inconsistent and labor-intensive manual coding practices. Here, we present an innovative framework that leverages a fine-tuned large language model to automatically infer DHAs from textual crash narratives, thereby improving the validity and interpretability of DHA classifications. Using five years of two-vehicle crash data from MTCF, we fine-tuned the Llama 3.2 1B model on detailed crash narratives and benchmarked its performance against conventional machine learning classifiers, including Random Forest, XGBoost, CatBoost, and a neural network. The fine-tuned LLM achieved an overall accuracy of 80%, surpassing all baseline models and demonstrating pronounced improvements in scenarios with imbalanced data. To increase interpretability, we developed a probabilistic reasoning approach, analyzing model output shifts across original test sets and three targeted counterfactual scenarios: variations in driver distraction and age. Our analysis revealed that introducing distraction for one driver substantially increased the likelihood of "General Unsafe Driving"; distraction for both drivers maximized the probability of "Both Drivers Took Hazardous Actions"; and assigning a teen driver markedly elevated the probability of "Speed and Stopping Violations." Our framework and analytical methods provide a robust and interpretable solution for large-scale automated DHA detection, offering new opportunities for traffic safety analysis and intervention.

DoorDash is getting in the car with General Motors' Cruise autonomous-vehicles to bring people food and groceries. General Motors has donated its first self-driving car, a 3-year-old Chevy Bolt electric car modified for autonomous operation, to the Henry Ford Museum. The car, GM Cruise Automation 01, will be on display immediately. "It'll be right at the front of the auto display, where we explain to people what a car is," The Henry Ford transportation curator Matt Anderson said Tuesday. The white hatchback, which sprouts sensors like a cat's whiskers, will be next to a '59 Cadillac in the museum's "Driving America" collection.

Tesla and SpaceX CEO Elon Musk has repeatedly said society needs to be more concerned about safety with the increased use of artificial intelligence. "If you're not concerned about AI safety, you should be," Musk recently tweeted. Jenny Dearborn, chief learning officer at software solutions company SAP, agrees. In fact, she says it's critical to educate ourselves on artificial intelligence and how to best use it. "Artificial intelligence will be everywhere," she tells CNBC Make It. "It will be the most prevalent aspect of our society that won't be visibly seen. But it will be behind everything."

Tesla and SpaceX CEO Elon Musk has repeatedly said society needs to be more concerned about safety with the increased use of artificial intelligence. "If you're not concerned about AI safety, you should be," Musk recently tweeted. Jenny Dearborn, chief learning officer at software solutions company SAP, agrees. In fact, she says it's critical to educate ourselves on artificial intelligence and how to best use it. "Artificial intelligence will be everywhere," she tells CNBC Make It. "It will be the most prevalent aspect of our society that won't be visibly seen. But it will be behind everything."

The area around Hillview Avenue in Palo Alto is dotted with well-known tech innovators: Xerox's PARC, Microsoft's Skype, VMware Inc. and HP Labs, among others. Amid the research centers and campuses of these tech stalwarts is another well-known company, but one whose name might seem somewhat out of place among these Silicon Valley trailblazers. Ford Motor Co. F, 1.32% is hoping to change that. Last year, the auto giant hung its shingle outside what it calls the Ford Research and Innovation Center, Palo Alto, as it seeks to embrace technology's disruption of its 100-plus-year-old business. With personal auto ownership as passe as telephone landlines to a new generation of consumers, electric-car powerhouse Tesla Motors Inc. TSLA, 1.27% -- also based in Palo Alto--upending the industry, and self-driving vehicles predicted in our future, Ford, like most auto makers around the world, is behind the proverbial eight ball. The automotive pioneer that developed the first mass produced, affordable car is experiencing the "innovator's dilemma," a conundrum faced by leading companies when a new, often cheaper, "good enough" technology breaks into its market dominance.

Just mention artificial intelligence or AI and the imaginative mind conjures up images of Terminator machines taking over the world. Thankfully, today's picture is much more positive. Businesses are beginning to harness the power of AI and robotics to grow profit. Many use the technology to collaborate with their staff. Artificial intelligence, meaning the ability of computers to make judgments, suddenly appeared real in the 1990s when computers began to beat chess world champions. Its sophistication has improved dramatically and this year Google's DeepMind won the immensely complicated Go board game.