Silicon Valley's battle against AI regulation is already shaping the next US election cycle. Silicon Valley is already pouring tens of millions of dollars into the midterm elections taking place across the US in 2026, as the tech industry's war over AI regulation moves decisively into American politics. Technology executives, investors, and companies tied to the AI boom are funding a new network of AI-focused super PACS, which is poised to make AI a major issue in this year's state and federal elections races. The election spending marks a sharp escalation of the AI regulation debate that has divided Silicon Valley for years. In the absence of federal action, state lawmakers in New York, California, and Colorado have passed laws in the past year requiring large AI developers to disclose safety practices and assess risks such as algorithmic discrimination.

President Donald Trump criticizes 'Woke AI' and excessive state regulation while House Republican leaders consider including AI preemption language in defense legislation.

A 10-year moratorium on state-level AI regulation included in President Donald Trump's "Big Beautiful Bill" has brushed up against a mounting battle over the growth of data centers. On Thursday, Representative Thomas Massie, a Kentucky Republican, posted on X that the megabill's 10-year block on states regulating artificial intelligence could "make it easier for corporations to get zoning variances, so massive AI data centers could be built in close proximity to residential areas." Massie, who did not vote for the bill, followed up his initial tweet with a screenshot of a story on a proposed data center in Oldham County, Kentucky, which downsized and changed locations following local pushback. "This isn't a conspiracy theory; this was a recent issue in my Congressional district," he wrote of concerns over the placement of data centers. "It was resolved at the local level because local officials had leverage. The big beautiful bill undermines the ability of local communities to decide where the AI data centers will be built."

Retrieval Augmented Generation (RAG) has emerged as a new paradigm for enhancing Large Language Model reliability through integration with external knowledge sources. However, efficient deployment of these systems presents significant technical challenges due to their inherently heterogeneous computational pipelines comprising LLMs, databases, and specialized processing components. We introduce Patchwork, a comprehensive end-to-end RAG serving framework designed to address these efficiency bottlenecks. Patchwork's architecture offers three key innovations: First, it provides a flexible specification interface enabling users to implement custom RAG pipelines. Secondly, it deploys these pipelines as distributed inference systems while optimizing for the unique scalability characteristics of individual RAG components. Third, Patchwork incorporates an online scheduling mechanism that continuously monitors request load and execution progress, dynamically minimizing SLO violations through strategic request prioritization and resource auto-scaling. Our experimental evaluation across four distinct RAG implementations demonstrates that Patchwork delivers substantial performance improvements over commercial alternatives, achieving throughput gains exceeding 48% while simultaneously reducing SLO violations by ~24%.

This paper introduces Patched Round-Trip Correctness (Patched RTC), a novel evaluation technique for Large Language Models (LLMs) applied to diverse software development tasks, particularly focusing on "outer loop" activities such as bug fixing, code review, and documentation updates. Patched RTC extends the original Round-Trip Correctness method to work with any LLM and downstream task, offering a self-evaluating framework that measures consistency and robustness of model responses without human intervention. The study demonstrates a correlation between Patched RTC scores and task-specific accuracy metrics, presenting it as an alternative to the LLM-as-Judge paradigm for open-domain task evaluation. We implement Patched RTC in an open-source framework called patchwork, allowing for transparent evaluation during inference across various patchflows. Experiments comparing GPT-3.5 and GPT-4 models across different software development tasks reveal that Patched RTC effectively distinguishes model performance and task difficulty. The paper also explores the impact of consistency prompts on improving model accuracy, suggesting that Patched RTC can guide prompt refinement and model selection for complex software development workflows.

Machine learning (ML) in healthcare presents numerous opportunities for enhancing patient care, population health, and healthcare providers' workflows. However, the real-world clinical and cost benefits remain limited due to challenges in data privacy, heterogeneous data sources, and the inability to fully leverage multiple data modalities. In this perspective paper, we introduce "patchwork learning" (PL), a novel paradigm that addresses these limitations by integrating information from disparate datasets composed of different data modalities (e.g., clinical free-text, medical images, omics) and distributed across separate and secure sites. PL allows the simultaneous utilization of complementary data sources while preserving data privacy, enabling the development of more holistic and generalizable ML models. We present the concept of patchwork learning and its current implementations in healthcare, exploring the potential opportunities and applicable data sources for addressing various healthcare challenges. PL leverages bridging modalities or overlapping feature spaces across sites to facilitate information sharing and impute missing data, thereby addressing related prediction tasks. We discuss the challenges associated with PL, many of which are shared by federated and multimodal learning, and provide recommendations for future research in this field. By offering a more comprehensive approach to healthcare data integration, patchwork learning has the potential to revolutionize the clinical applicability of ML models. This paradigm promises to strike a balance between personalization and generalizability, ultimately enhancing patient experiences, improving population health, and optimizing healthcare providers' workflows. Introduction Machine learning (ML) in healthcare is a rapidly evolving field, presenting numerous opportunities for progress. Active and passive patient data collection, both during and outside medical care, can be utilized to address health challenges. As a result, ML has become an essential tool for processing and analyzing these data in various domains, including natural language processing, computer vision, and more. ML systems have demonstrated their potential to enhance patient experiences, improve population health, reduce per capita healthcare costs, and optimize healthcare providers' workflows Data privacy is a major challenge facing the use of ML in healthcare, as it restricts the potential for pooling electronic health record (EHR) data from multiple sites. While single modality models exist (e.g., clinical notes, lab tests, omics, or medical images), systems that simultaneously leverage multiple modalities are relatively scarce. MML combines disparate data sources to capitalize on complementary information, thereby improving performance.

Hollywood has colourful notions about artificial intelligence (AI). The popular image is a future where robot armies spontaneously turn to malevolence, pitching humanity in a battle against extinction. In reality, the risks posed by AI today are more insidious and harder to unpick. They are often a by-product of the technology's seemingly endless application in modern society and increasing role in everyday life, perhaps best highlighted by Microsoft's latest multi-billion-dollar investment into ChatGPT-maker OpenAI. Either way, it's unsurprising that AI generates so much debate, not least in how we can build regulatory safeguards to ensure we master the technology, rather than surrender control to the machines. Right now, we tackle AI using a patchwork of laws and regulations, as well as guidance that doesn't have the force of law. Against this backdrop, it's clear that current frameworks are likely to change – perhaps significantly.

Novel plant communities reshape landscapes and pose challenges for land cover classification and mapping that can constrain research and stewardship efforts. In the US Northeast, emergence of low-statured woody vegetation, or shrublands, instead of secondary forests in post-agricultural landscapes is well-documented by field studies, but poorly understood from a landscape perspective, which limits the ability to systematically study and manage these lands. To address gaps in classification/mapping of low-statured cover types where they have been historically rare, we developed models to predict shrubland distributions at 30m resolution across New York State (NYS), using a stacked ensemble combining a random forest, gradient boosting machine, and artificial neural network to integrate remote sensing of structural (airborne LIDAR) and optical (satellite imagery) properties of vegetation cover. We first classified a 1m canopy height model (CHM), derived from a patchwork of available LIDAR coverages, to define shrubland presence/absence. Next, these non-contiguous maps were used to train a model ensemble based on temporally-segmented imagery to predict shrubland probability for the entire study landscape (NYS). Approximately 2.5% of the CHM coverage area was classified as shrubland. Models using Landsat predictors trained on the classified CHM were effective at identifying shrubland (test set AUC=0.893, real-world AUC=0.904), in discriminating between shrub/young forest and other cover classes, and produced qualitatively sensible maps, even when extending beyond the original training data. Our results suggest that incorporation of airborne LiDAR, even from a discontinuous patchwork of coverages, can improve land cover classification of historically rare but increasingly prevalent shrubland habitats across broader areas.

Estimating forest AGB at large scales and fine spatial resolutions has become increasingly important for greenhouse gas accounting, monitoring, and verification efforts to mitigate climate change. Airborne LiDAR is highly valuable for modeling attributes of forest structure including AGB, yet most LiDAR collections take place at local or regional scales covering irregular, non-contiguous footprints, resulting in a patchwork of different landscape segments at various points in time. Here, as part of a statewide forest carbon assessment for New York State (USA), we addressed common obstacles in leveraging a LiDAR patchwork for AGB mapping at landscape scales, including selection of training data, the investigation of regional or coverage specific patterns in prediction error, and map agreement with field inventory across multiple scales. Three machine learning algorithms and an ensemble model were trained with FIA field measurements, airborne LiDAR, and topographic, climatic and cadastral geodata. Using a strict set of plot selection criteria, 801 FIA plots were selected with co-located point clouds drawn from a patchwork of 17 leaf-off LiDAR coverages (2014-2019). Our ensemble model was used to produce 30 m AGB prediction surfaces within a predictor-defined area of applicability (98% of LiDAR coverage), and the resulting AGB maps were compared with FIA plot-level and areal estimates at multiple scales of aggregation. Our model was overall accurate (% RMSE 22-45%; MAE 11.6-29.4 Mg ha$^{-1}$; ME 2.4-6.3 Mg ha$^{-1}$), explained 73-80% of field-observed variation, and yielded estimates that were consistent with FIA's design-based estimates (89% of estimates within FIA's 95% CI). We share practical solutions to challenges faced in using spatiotemporal patchworks of LiDAR to meet growing needs for AGB mapping in support of applications in forest carbon accounting and ecosystem.

Henry Alty argues that while robotic process automation players like Blue Prism and UiPath started companies on the automation journey, businesses need to think more strategically to capture value from broader digital transformation. The rise of robotic process automation (RPA) saw companies automate individual tasks previously undertaken by humans, utilising software provided by companies including Blue Prism and UiPath. At one point valued at more than £1bn and $35bn respectively, these venture capital darlings flew high on the promise of turning an entire workforce into'citizen developers', who could effortlessly develop applications to solve individual problems. This software was sold to Chief Financial Officers as a tool to drive enormous productivity gains and cost savings by automating repetitive'swivel chair' work. But that promise has been largely disproven.