A nonlinear-dynamical algorithm for city planning is proposed as an Impulse Pattern Formulation (IPF) for predicting relevant parameters like health, artistic freedom, or financial developments of different social or political stakeholders over the cause of a planning process. The IPF has already shown high predictive precision at low computational cost in musical instrument simulations, brain dynamics, and human-human interactions. The social and political IPF consists of three basic equations of system state developments, self-adaptation of stakeholders, two adaptive interactions, and external impact terms suitable for respective planning situations. Typical scenarios of stakeholder interactions and developments are modeled by adjusting a set of system parameters. These include stakeholder reaction to external input, enhanced system stability through self-adaptation, stakeholder convergence due to adaptive interaction, as well as complex dynamics in terms of fixed stakeholder impacts. A workflow for implementing the algorithm in real city planning scenarios is outlined. This workflow includes machine learning of a suitable set of parameters suggesting best-practice planning to aim at the desired development of the planning process and its output.

Trustworthy capability evaluations are crucial for ensuring the safety of AI systems, and are becoming a key component of AI regulation. However, the developers of an AI system, or the AI system itself, may have incentives for evaluations to understate the AI's actual capability. These conflicting interests lead to the problem of sandbagging $\unicode{x2013}$ which we define as "strategic underperformance on an evaluation". In this paper we assess sandbagging capabilities in contemporary language models (LMs). We prompt frontier LMs, like GPT-4 and Claude 3 Opus, to selectively underperform on dangerous capability evaluations, while maintaining performance on general (harmless) capability evaluations. Moreover, we find that models can be fine-tuned, on a synthetic dataset, to hide specific capabilities unless given a password. This behaviour generalizes to high-quality, held-out benchmarks such as WMDP. In addition, we show that both frontier and smaller models can be prompted, or password-locked, to target specific scores on a capability evaluation. Even more, we found that a capable password-locked model (Llama 3 70b) is reasonably able to emulate a less capable model (Llama 2 7b). Overall, our results suggest that capability evaluations are vulnerable to sandbagging. This vulnerability decreases the trustworthiness of evaluations, and thereby undermines important safety decisions regarding the development and deployment of advanced AI systems.

Most public instruction finetuning datasets are relatively small compared to the closed source datasets used to train industry models. To study questions about finetuning at scale, such as curricula and learning rate cooldown schedules, there is a need for industrial-scale datasets. However, this scale necessitates a data generation process that is almost entirely automated. In this work, we study methods for generating large instruction datasets from a single prompt. With little human oversight, we get LLMs to write diverse sets of instruction examples ranging from simple completion tasks to complex multi-turn dialogs across a variety of subject areas. When finetuning a Llama-3 8B base model, our dataset meets or exceeds both WizardLM and Ultrachat on both knowledge-intensive leaderboard tasks as well as conversational evaluations. We release our dataset, the "generator" prompts that created it, and our finetuned model checkpoints.

Traditional federated learning (FL) methods have limited support for clients with varying computational and communication abilities, leading to inefficiencies and potential inaccuracies in model training. This limitation hinders the widespread adoption of FL in diverse and resource-constrained environments, such as those with client devices ranging from powerful servers to mobile devices. To address this need, this paper introduces Federated Learning with Flexible Architectures (FedFA), an FL training algorithm that allows clients to train models of different widths and depths. Each client can select a network architecture suitable for its resources, with shallower and thinner networks requiring fewer computing resources for training. Unlike prior work in this area, FedFA incorporates the layer grafting technique to align clients' local architectures with the largest network architecture in the FL system during model aggregation. Layer grafting ensures that all client contributions are uniformly integrated into the global model, thereby minimizing the risk of any individual client's data skewing the model's parameters disproportionately and introducing security benefits. Moreover, FedFA introduces the scalable aggregation method to manage scale variations in weights among different network architectures. Experimentally, FedFA outperforms previous width and depth flexible aggregation strategies. Furthermore, FedFA demonstrates increased robustness against performance degradation in backdoor attack scenarios compared to earlier strategies.

Understanding the business cycle is crucial for building economic stability, guiding business planning, and informing investment decisions. The business cycle refers to the recurring pattern of expansion and contraction in economic activity over time. Economic analysis is inherently complex, incorporating a myriad of factors (such as macroeconomic indicators, political decisions). This complexity makes it challenging to fully account for all variables when determining the current state of the economy and predicting its future trajectory in the upcoming months. The objective of this study is to investigate the capacity of machine learning models in automatically analyzing the state of the economic, with the goal of forecasting business phases (expansion, slowdown, recession and recovery) in the United States and the EuroZone. We compared three different machine learning approaches to classify the phases of the business cycle, and among them, the Multinomial Logistic Regression (MLR) achieved the best results. Specifically, MLR got the best results by achieving the accuracy of 65.25% (Top1) and 84.74% (Top2) for the EuroZone and 75% (Top1) and 92.14% (Top2) for the United States. These results demonstrate the potential of machine learning techniques to predict business cycles accurately, which can aid in making informed decisions in the fields of economics and finance.

Nakasone joins OpenAI's board following a dramatic board shake-up. Amid a tougher regulatory environment and increased efforts to digitize government and military services, tech companies are increasingly seeking board members with military expertise. Amazon's board includes Keith Alexander, who was previously the commander of U.S. Cyber Command and the director of the NSA. Google Public Sector, a division of the company that focuses on selling cloud services to governments, also has retired generals on its board.

In a bizarre turn of events, two AI chatbots are running for elected office for the first time--ever. VIC is campaigning for mayor in Cheyenne, Wyoming, and AI Steve is running for Parliament in the UK. Reporter Vittoria Elliot interviewed both of the bots and the people behind them. She explains their motivations, and if any of this is even legal. Meanwhile, reporter David Gilbert talks about how Google and Microsofts' AI chatbots are refusing to confirm who won the 2020 election.

Pope Francis accused conservative bishops in the U.S. of holding a "suicidal attitude" in a new interview with CBS News that aired on Sunday. Pope Francis will meet with the leaders of the United States, Ukraine, France and India on the sidelines of the Group of 7 (G-7) summit in Italy's Borgo Egnazia, the Vatican said on Thursday. Francis, who in January warned against the "perverse" dangers of artificial intelligence, is due to take part in leaders' talks on the new technology on Friday. He is the first pope to take part in G-7 discussions. Pope Francis is seen at the weekly general audience at Saint Peter's Square at the Vatican on June 12, 2024.

Tech watchers and nerds like me get excited by tools such as ChatGPT. They look set to improve our lives in many ways – and hopefully augment our jobs rather than replace them. But in general, the public hasn't been so enamoured of the AI "revolution". Make no mistake: artificial intelligence will have a transformative effect on how we live and work – it is already being used to draft legal letters and analyse lung-cancer scans. ChatGPT was also the fastest-growing app in history after it was released. That said, four in 10 Britons haven't heard of ChatGPT, according to a recent survey by the University of Oxford, and only 9% use it weekly or more frequently.

Alex Galvagni, CEO of Age of Learning and a former artificial intelligence researcher with NASA, says advances in AI now make it possible to deliver to children "a personalized and supportive" experience in education. Artificial intelligence delivered advances to the U.S. space program and to medicine decades before it made headlines. Now, AI is poised to bring major improvements to American education, tech entrepreneur Alex Galvagni said in an exclusive interview in New York City with Fox News Digital. Galvagni is CEO of Age of Learning, the California-based company behind popular school-room products such as ABCmouse Early Learning Academy. "AI has been with us a long time. Research was happening as early as the 1950s," he said.