Just a few days ago, OpenAI's usage policies page explicitly states that the company prohibits the use of its technology for "military and warfare" purposes. That line has since been deleted. As first noticed by The Intercept, the company updated the page on January 10 "to be clearer and provide more service-specific guidance," as the changelog states. It still prohibits the use of its large language models (LLMs) for anything that can cause harm, and it warns people against using its services to "develop or use weapons." However, the company has removed language pertaining to "military and warfare."

Some companies are already aware that the use of the term AI has become counter-productive. One product that has had rave reviews this year at CES is called R1, made by Rabbit. The phone like device uses a form of generative AI - and allows users to circumvent apps, and simply ask for things to be done.

In this article, we review the literature on statistical theories of neural networks from three perspectives. In the first part, results on excess risks for neural networks are reviewed in the nonparametric framework of regression or classification. These results rely on explicit constructions of neural networks, leading to fast convergence rates of excess risks, in that tools from the approximation theory are adopted. Through these constructions, the width and depth of the networks can be expressed in terms of sample size, data dimension, and function smoothness. Nonetheless, their underlying analysis only applies to the global minimizer in the highly non-convex landscape of deep neural networks. This motivates us to review the training dynamics of neural networks in the second part. Specifically, we review papers that attempt to answer ``how the neural network trained via gradient-based methods finds the solution that can generalize well on unseen data.'' In particular, two well-known paradigms are reviewed: the Neural Tangent Kernel (NTK) paradigm, and Mean-Field (MF) paradigm. In the last part, we review the most recent theoretical advancements in generative models including Generative Adversarial Networks (GANs), diffusion models, and in-context learning (ICL) in the Large Language Models (LLMs). The former two models are known to be the main pillars of the modern generative AI era, while ICL is a strong capability of LLMs in learning from a few examples in the context. Finally, we conclude the paper by suggesting several promising directions for deep learning theory.

In 2019, Mr. Nadella made Microsoft's first of several investments in OpenAI, the start-up that would build the A.I.-powered ChatGPT chatbot. In the end of the summer of 2022, he was impressed by a preview of OpenAI's underlying technology, known as GPT-4, and soon began prodding Microsoft to add generative A.I. to its products at what he called a "frantic pace." He started with adding a chatbot to the Bing search engine, but then began pushing A.I. into the Windows operating system and productive applications like Excel and Outlook, and offering OpenAI's systems to customers of Azure, Microsoft's flagship cloud computing product. The revenue has only just started to show up in Microsoft's financial results. Generative A.I. accounted for about three percentage points of growth to Azure in the three months that ended in September, and the 30-a-month offering inside Microsoft's productivity software began a general release only in November. This isn't the first time that Microsoft has pulled ahead of Apple in recent years.

ChatGPT has certainly captured the world's imagination since its release at the end of 2022. But in day-to-day life, it is still a relatively niche product--a curiosity that leads people to ask questions that begin "Have you tried …?" or "What do you think about …?" Its maker, OpenAI, has a much more expansive vision. Its aim is seemingly to completely remake how people use the internet. For that to happen, the bot needs to be more than a conversation starter: It has to be a functioning business.

The rise of AI means computers are better at understanding us and finding what we want than ever before. As a result, big tech companies like Apple and OpenAI are offering new ways of interacting with computers that bypass traditional displays, mice and keyboards. Will screens soon become a thing of the past? How this moment for AI will change society forever (and how it won't)

House Speaker Mike Johnson met with OpenAI CEO Sam Altman at the U.S. Capitol on Thursday to discuss what kind of role Congress has to play in legislating on artificial intelligence. "It was a very good meeting," Johnson told reporters afterward. "We talked about where we are with regard to the approach of Congress to AI." He said they had a "very thoughtful discussion" about how the Senate and House can forge a bipartisan path forward. House Speaker Mike Johnson, left, and OpenAI CEO Sam Altman.

We're almost guaranteed to get the first official details about the Galaxy S24 smartphones, which are almost certainly going to have on-device generative AI features. You'll be able to watch Samsung Unpacked at 1PM ET on January 17 on the company's website or YouTube channel. Samsung hasn't exactly been subtle about what's on deck for Unpacked. Yeah, it's pretty safe to say AI will be a focal point of the showcase. In November, Samsung revealed its Gauss generative AI models.

The release of ChatGPT in November 2022 prompted a massive uptake of generative artificial intelligence (GenAI) across higher education institutions (HEIs). HEIs scrambled to respond to its use, especially by students, looking first to regulate it and then arguing for its productive integration within teaching and learning. In the year since the release, HEIs have increasingly provided policies and guidelines to direct GenAI. In this paper we examined documents produced by 116 US universities categorized as high research activity or R1 institutions to comprehensively understand GenAI related advice and guidance given to institutional stakeholders. Through an extensive analysis, we found the majority of universities (N=73, 63%) encourage the use of GenAI and many provide detailed guidance for its use in the classroom (N=48, 41%). More than half of all institutions provided sample syllabi (N=65, 56%) and half (N=58, 50%) provided sample GenAI curriculum and activities that would help instructors integrate and leverage GenAI in their classroom. Notably, most guidance for activities focused on writing, whereas code and STEM-related activities were mentioned half the time and vaguely even when they were (N=58, 50%). Finally, more than one half of institutions talked about the ethics of GenAI on a range of topics broadly, including Diversity, Equity and Inclusion (DEI) (N=60, 52%). Overall, based on our findings we caution that guidance for faculty can become burdensome as extensive revision of pedagogical approaches is often recommended in the policies.

Geospatial Location Embedding (GLE) helps a Large Language Model (LLM) assimilate and analyze spatial data. GLE emergence in Geospatial Artificial Intelligence (GeoAI) is precipitated by the need for deeper geospatial awareness in our complex contemporary spaces and the success of LLMs in extracting deep meaning in Generative AI. We searched Google Scholar, Science Direct, and arXiv for papers on geospatial location embedding and LLM and reviewed articles focused on gaining deeper spatial "knowing" through LLMs. We screened 304 titles, 30 abstracts, and 18 full-text papers that reveal four GLE themes - Entity Location Embedding (ELE), Document Location Embedding (DLE), Sequence Location Embedding (SLE), and Token Location Embedding (TLE). Synthesis is tabular and narrative, including a dialogic conversation between "Space" and "LLM." Though GLEs aid spatial understanding by superimposing spatial data, they emphasize the need to advance in the intricacies of spatial modalities and generalized reasoning. GLEs signal the need for a Spatial Foundation/Language Model (SLM) that embeds spatial knowing within the model architecture. The SLM framework advances Spatial Artificial Intelligence Systems (SPAIS), establishing a Spatial Vector Space (SVS) that maps to physical space. The resulting spatially imbued Language Model is unique. It simultaneously represents actual space and an AI-capable space, paving the way for AI native geo storage, analysis, and multi-modality as the basis for Spatial Artificial Intelligence Systems (SPAIS).