Multi-agent large language model simulations have the potential to model complex human behaviors and interactions. If the mechanics are set up properly, unanticipated and valuable social dynamics can surface. However, it is challenging to consistently enforce simulation mechanics while still allowing for notable and emergent dynamics. We present AgentDynEx, an AI system that helps set up simulations from user-specified mechanics and dynamics. AgentDynEx uses LLMs to guide users through a Configuration Matrix to identify core mechanics and define milestones to track dynamics. It also introduces a method called \textit{nudging}, where the system dynamically reflects on simulation progress and gently intervenes if it begins to deviate from intended outcomes. A technical evaluation found that nudging enables simulations to have more complex mechanics and maintain its notable dynamics compared to simulations without nudging. We discuss the importance of nudging as a technique for balancing mechanics and dynamics of multi-agent simulations.

Interior design is a complex and creative discipline involving aesthetics, functionality, ergonomics, and materials science. Effective solutions must meet diverse requirements, typically producing multiple deliverables such as renderings and design drawings from various perspectives. Consequently, interior design processes are often inefficient and demand significant creativity. With advances in machine learning, generative models have emerged as a promising means of improving efficiency by creating designs from text descriptions or sketches. However, few generative works focus on interior design, leading to substantial discrepancies between outputs and practical needs, such as differences in size, spatial scope, and the lack of controllable generation quality. To address these challenges, we propose DiffDesign, a controllable diffusion model with meta priors for efficient interior design generation. Specifically, we utilize the generative priors of a 2D diffusion model pre-trained on a large image dataset as our rendering backbone. We further guide the denoising process by disentangling cross-attention control over design attributes, such as appearance, pose, and size, and introduce an optimal transfer-based alignment module to enforce view consistency. Simultaneously, we construct an interior design-specific dataset, DesignHelper, consisting of over 400 solutions across more than 15 spatial types and 15 design styles. This dataset helps fine-tune DiffDesign. Extensive experiments conducted on various benchmark datasets demonstrate the effectiveness and robustness of DiffDesign.

The Pentagon for the first time publicly released drone footage of a botched strike in Kabul that killed 10 members of a family, including seven children, amid the chaotic US withdrawal from the country. The footage was initially obtained through a Freedom of Information Act lawsuit by The New York Times and was subsequently released by US Central Command on Thursday. It appears to underscore how, by the Pentagon's own account, limited intelligence, a heightened state of alert, and rushed decision-making led to the killing of civilians. The fuzzy footage, which officials told the newspaper was recorded by two MQ-9 Reaper drones, shows the moments before the fatal drone strike on a car in a courtyard in Kabul on August 29. One segment of footage appears to show a shorter, blurry figure in white next to a taller figure in black in the courtyard as the targeted car backs in to park, according to the analysis by the Times.

Kabul – It was the last known missile fired by the United States in its 20-year war in Afghanistan, and the military called it a "righteous strike" -- a drone attack after hours of surveillance Aug. 29 against a vehicle that U.S. officials thought contained an Islamic State bomb and posed an imminent threat to troops at Kabul's airport. But a New York Times investigation of video evidence, along with interviews with more than a dozen of the driver's co-workers and family members in Kabul, raises doubts about the U.S. version of events, including whether explosives were present in the vehicle, whether the driver had a connection to the Islamic State group and whether there was a second explosion after the missile struck the car. Military officials said they did not know the identity of the car's driver when the drone fired but deemed him suspicious because of how they interpreted his activities that day, saying that he possibly visited an Islamic State group safe house and, at one point, loaded what they thought could be explosives into the car. Times reporting has identified the driver as Zemari Ahmadi, a longtime worker for a U.S. aid group. The evidence, including extensive interviews with family members, co-workers and witnesses, suggests that his travels that day actually involved transporting colleagues to and from work.

Text description provided by the architects. In Yangliu Park near the AI technology city of Xiangjiang New District is the Xiangjiang Artificial Intelligence Technology Valley. As the parlor serving the city, the valley offers indoor and outdoor exhibitions, meetings, exchanges, receptions, and multiple services. Here we can learn and explore future frontier technology. In a picturesque park, this is also a nice place for leisure activities.

Danish architecture studio BIG has designed Terminus AI City Operating System as a campus in Chongqing, China, that will be operated by an artificial intelligence system. BIG has drawn up the plans for smart service specialists Terminus Group, which will have its headquarters at the centre of the artificial intelligence-run city campus. Called Terminus AI City Operating System, or TACOS, everything in the city from the fire service to personal butlers would be operated by this AI. The development will be located in Chongqing Hi-Tech Industrial Development Zone and will include Cloud Valley, a campus-style headquarters for Terminus Group. "We are excited to build an in-depth partnership with Terminus Group," said Ingels.

'we have over the recent years worked with several of the world's leading technology companies,' says bjarke ingels, founder & creative director of BIG-bjarke ingels group. 'we are thrilled to bring our experience to chongqing and together with terminus create AI CITY, the first landmark project in the hi-tech zone to become a new center of innovation for china. AI CITY is envisioned as a city where people, technology and nature thrive together -- with spaces designed for all types of life: human life, plant life, animal life and even artificial life.' AI CITY seeks to provide terminus, and the world's leading tech companies, with a place to advance the future of artificial intelligence and robotics, and build the foundations of a new sustainable development. BIG says that the roofscape is one of the project's most important components.