AI chatbots can sway voters' political views, studies say Paris - A brief conversation with a partisan AI chatbot can influence voters' political views, studies published Thursday found, with evidence-backed arguments -- true or not -- proving particularly persuasive. Experiments with generative artificial intelligence models, such as OpenAI's GPT-4o and Chinese alternative DeepSeek, found they were able to shift supporters of Republican Donald Trump toward his Democratic opponent Kamala Harris by almost four points on a 100-point scale ahead of the 2024 U.S. presidential election. Opposition supporters in 2025 polls in Canada and Poland meanwhile had their views shifted by up to 10 points after chatting with a bot programmed to persuade. In a time of both misinformation and too much information, quality journalism is more crucial than ever. By subscribing, you can help us get the story right.

OpenAI CEO Sam Altman scrambles to boost ChatGPT's quality and first lady Melania Trump rolls out an AI-powered Spanish translation of her memoir.

Here's What You Should Know About Launching an AI Startup AI startups say the promise of turning dazzling models into useful products is harder than anyone expected. Three founders discuss what it takes. Julie Bornstein thought it would be a cinch to implement her idea for an AI startup . Her résumé in digital commerce is impeccable: VP of ecommerce at Nordstrom, COO of the startup Stitch Fix, and founder of a personalized shopping platform acquired by Pinterest . Fashion has been her obsession since she was a Syracuse high schooler inhaling spreads in Seventeen and hanging out in local malls.

We asked teachers about their experiences with AI in the classroom -- here's what they said Since ChatGPT and other large language models burst into public consciousness, school boards are drafting policies, universities are hosting symposiums and tech companies are relentlessly promoting their latest AI-powered learning tools . In the race to modernize education, artificial intelligence (AI) has become the new darling of policy innovation. While AI promises efficiency and personalization, it also introduces complexity, ethical dilemmas and new demands . Teachers, who are at the heart of learning along with students, are watching this transformation with growing unease. For example, according to the Alberta Teachers' Association, 80 to 90 per cent of educators surveyed expressed concern about AI's potential negative effects on education.

Plus: The metaverse's future looks murkier than ever. Chatting with a politically biased AI model is more effective than political ads at nudging both Democrats and Republicans to support presidential candidates of the opposing party, new research shows. The chatbots swayed opinions by citing facts and evidence, but they were not always accurate--in fact, the researchers found, the most persuasive models said the most untrue things. The findings are the latest in an emerging body of research demonstrating the persuasive power of LLMs. They raise profound questions about how generative AI could reshape elections. The fear that elections could be overwhelmed by AI-generated realistic fake media has gone mainstream--and for good reason.

Microsoft's Copilot+ AI PC plan fizzled, but it still served a purpose At least Microsoft was able to reshape premium PCs. Microsoft's Copilot+ initiative launched last year with a clear goal: To produce capable laptops for people eagerly anticipating AI-powered features. Read that sentence again, and it's glaringly obvious that Microsoft's plan was flawed from the start. Most consumers aren't nearly as hyped for AI features as the companies eager to foist artificial intelligence upon us. Microsoft's Recall -- which snaps screenshots of your PC to create a database of everything you've done-was dogged by privacy concerns from the start.

AI is eminently capable of political persuasion and could automate it at a mass scale. In January 2024, the phone rang in homes all around New Hampshire. On the other end was Joe Biden's voice, urging Democrats to "save your vote" by skipping the primary. It sounded authentic, but it wasn't. The call was a fake, generated by artificial intelligence. Today, the technology behind that hoax looks quaint.

Big Tech has lost its way. At WIRED's Big Interview event, Techdirt editor Mike Masnick and Common Tools CEO Alex Komoroske announced a manifesto designed to help the industry get back on track. Alex Komoroske has always been at odds with Big Tech's darker side. Though he cut his product-management teeth at Google and Stripe, he was never comfortable with the industry's increasing prioritization of profits over people. Once during his time at Google, he extolled the societal benefits of a project only to be met with, "Oh Alex, you'd be a VP by now if you just stopped thinking through the implications of your actions."

This thesis develops methods for causal inference and causal representation learning (CRL) in high-dimensional, time-varying data. The first contribution introduces the Causal Dynamic Variational Autoencoder (CDVAE), a model for estimating Individual Treatment Effects (ITEs) by capturing unobserved heterogeneity in treatment response driven by latent risk factors that affect only outcomes. CDVAE comes with theoretical guarantees on valid latent adjustment and generalization bounds for ITE error. Experiments on synthetic and real datasets show that CDVAE outperforms baselines, and that state-of-the-art models greatly improve when augmented with its latent substitutes, approaching oracle performance without access to true adjustment variables. The second contribution proposes an efficient framework for long-term counterfactual regression based on RNNs enhanced with Contrastive Predictive Coding (CPC) and InfoMax. It captures long-range dependencies under time-varying confounding while avoiding the computational cost of transformers, achieving state-of-the-art results and introducing CPC into causal inference. The third contribution advances CRL by addressing how latent causes manifest in observed variables. We introduce a model-agnostic interpretability layer based on the geometry of the decoder Jacobian. A sparse self-expression prior induces modular, possibly overlapping groups of observed features aligned with shared latent influences. We provide recovery guarantees in both disjoint and overlapping settings and show that meaningful latent-to-observed structure can be recovered without anchor features or single-parent assumptions. Scalable Jacobian-based regularization techniques are also developed.

We develop a flexible feature selection framework based on deep neural networks that approximately controls the false discovery rate (FDR), a measure of Type-I error. The method applies to architectures whose first layer is fully connected. From the second layer onward, it accommodates multilayer perceptrons (MLPs) of arbitrary width and depth, convolutional and recurrent networks, attention mechanisms, residual connections, and dropout. The procedure also accommodates stochastic gradient descent with data-independent initializations and learning rates. To the best of our knowledge, this is the first work to provide a theoretical guarantee of FDR control for feature selection within such a general deep learning setting. Our analysis is built upon a multi-index data-generating model and an asymptotic regime in which the feature dimension $n$ diverges faster than the latent dimension $q^{*}$, while the sample size, the number of training iterations, the network depth, and hidden layer widths are left unrestricted. Under this setting, we show that each coordinate of the gradient-based feature-importance vector admits a marginal normal approximation, thereby supporting the validity of asymptotic FDR control. As a theoretical limitation, we assume $\mathbf{B}$-right orthogonal invariance of the design matrix, and we discuss broader generalizations. We also present numerical experiments that underscore the theoretical findings.