The news: Google DeepMind has launched a new watermarking tool which labels whether pictures have been generated with AI. The tool, called SynthID, will allow users to generate images using Google's AI image generator Imagen, then choose whether to add a watermark. Watermarking--a technique where you hide a signal in a piece of text or an image to identify it as AI-generated--has become one of the most popular policy suggestions to curb harms. These new tools could help protect our pictures from AI. PhotoGuard and Glaze are just two new systems designed to make it harder to tinker with photos using AI tools. The finding could strengthen artists' claims that AI companies are infringing their rights.

Microsoft has started a coalition of tech companies and media companies to develop a common standard for watermarking AI images, and the company has said it is researching new methods to track AI images. The company also places a small visible watermark in the corner of images generated by its AI tools. OpenAI, whose Dall-E image generator helped kick off the wave of interest in AI last year, also adds a visible watermark. AI researchers have suggested ways of embedding digital watermarks that the human eye can't see but can be identified by a computer.

Watermarking--a technique where you hide a signal in a piece of text or an image to identify it as AI-generated--has become one of the most popular ideas proposed to curb such harms. In July, the White House announced it had secured voluntary commitments from leading AI companies such as OpenAI, Google, and Meta to develop watermarking tools in an effort to combat misinformation and misuse of AI-generated content. At Google's annual conference I/O in May, CEO Sundar Pichai said the company is building its models to include watermarking and other techniques from the start. Google DeepMind is now the first Big Tech company to publicly launch such a tool. Traditionally images have been watermarked by adding a visible overlay onto them, or adding information into their metadata.

ChatGPT creator OpenAI has unveiled a business version of its artificial intelligence-powered chatbot as the California-based startup grapples with declining users and concerns about the potential harms of AI. ChatGPT Enterprise features improved security and privacy, with early corporate adopters including Carlyle, The Estée Lauder Companies and PwC, OpenAI said in a blog post on Monday. "We believe AI can assist and elevate every aspect of our working lives and make teams more creative and productive," OpenAI said. "Today marks another step towards an AI assistant for work that helps with any task, is customised for your organisation, and that protects your company data." ChatGPT Enterprise also features unlimited higher-speed GPT-4 access, longer context windows for processing longer inputs, advanced data analysis capabilities and customisation options, the company said. ChatGPT has been criticised by privacy experts for scooping up vast troves of internet data, including personal information and stolen data, without permission.

Teenagers deciding their future this year have a lot to contend with. In England, those who sat their A-levels suffered the biggest results drop on record while the top grades in GCSEs also fell. And now they face the question: will the career I choose to pursue even exist by the time I enter the workforce? Artificial intelligence has hit the mainstream with the popularity of generative AI programmes driven by large language models such as ChatGPT. Businesses are increasingly adopting the technology.

Recent advances in machine learning and AI, including Generative AI and LLMs, are disrupting technological innovation, product development, and society as a whole. AI's contribution to technology can come from multiple approaches that require access to large training data sets and clear performance evaluation criteria, ranging from pattern recognition and classification to generative models. Yet, AI has contributed less to fundamental science in part because large data sets of high-quality data for scientific practice and model discovery are more difficult to access. Generative AI, in general, and Large Language Models in particular, may represent an opportunity to augment and accelerate the scientific discovery of fundamental deep science with quantitative models. Here we explore and investigate aspects of an AI-driven, automated, closed-loop approach to scientific discovery, including self-driven hypothesis generation and open-ended autonomous exploration of the hypothesis space. Integrating AI-driven automation into the practice of science would mitigate current problems, including the replication of findings, systematic production of data, and ultimately democratisation of the scientific process. Realising these possibilities requires a vision for augmented AI coupled with a diversity of AI approaches able to deal with fundamental aspects of causality analysis and model discovery while enabling unbiased search across the space of putative explanations. These advances hold the promise to unleash AI's potential for searching and discovering the fundamental structure of our world beyond what human scientists have been able to achieve. Such a vision would push the boundaries of new fundamental science rather than automatize current workflows and instead open doors for technological innovation to tackle some of the greatest challenges facing humanity today.

Accurate trajectory prediction is crucial for the safe and efficient operation of autonomous vehicles. The growing popularity of deep learning has led to the development of numerous methods for trajectory prediction. While deterministic deep learning models have been widely used, deep generative models have gained popularity as they learn data distributions from training data and account for trajectory uncertainties. In this study, we propose EquiDiff, a deep generative model for predicting future vehicle trajectories. EquiDiff is based on the conditional diffusion model, which generates future trajectories by incorporating historical information and random Gaussian noise. The backbone model of EquiDiff is an SO(2)-equivariant transformer that fully utilizes the geometric properties of location coordinates. In addition, we employ Recurrent Neural Networks and Graph Attention Networks to extract social interactions from historical trajectories. To evaluate the performance of EquiDiff, we conduct extensive experiments on the NGSIM dataset. Our results demonstrate that EquiDiff outperforms other baseline models in short-term prediction, but has slightly higher errors for long-term prediction. Furthermore, we conduct an ablation study to investigate the contribution of each component of EquiDiff to the prediction accuracy. Additionally, we present a visualization of the generation process of our diffusion model, providing insights into the uncertainty of the prediction.

ChatGPT is a recent chatbot service released by OpenAI and is receiving increasing attention over the past few months. While evaluations of various aspects of ChatGPT have been done, its robustness, i.e., the performance to unexpected inputs, is still unclear to the public. Robustness is of particular concern in responsible AI, especially for safety-critical applications. In this paper, we conduct a thorough evaluation of the robustness of ChatGPT from the adversarial and out-of-distribution (OOD) perspective. To do so, we employ the AdvGLUE and ANLI benchmarks to assess adversarial robustness and the Flipkart review and DDXPlus medical diagnosis datasets for OOD evaluation. We select several popular foundation models as baselines. Results show that ChatGPT shows consistent advantages on most adversarial and OOD classification and translation tasks. However, the absolute performance is far from perfection, which suggests that adversarial and OOD robustness remains a significant threat to foundation models. Moreover, ChatGPT shows astounding performance in understanding dialogue-related texts and we find that it tends to provide informal suggestions for medical tasks instead of definitive answers. Finally, we present in-depth discussions of possible research directions.

Semantic editing of images is the fundamental goal of computer vision. Although deep learning methods, such as generative adversarial networks (GANs), are capable of producing high-quality images, they often do not have an inherent way of editing generated images semantically. Recent studies have investigated a way of manipulating the latent variable to determine the images to be generated. However, methods that assume linear semantic arithmetic have certain limitations in terms of the quality of image editing, whereas methods that discover nonlinear semantic pathways provide non-commutative editing, which is inconsistent when applied in different orders. This study proposes a novel method called deep curvilinear editing (DeCurvEd) to determine semantic commuting vector fields on the latent space. We theoretically demonstrate that owing to commutativity, the editing of multiple attributes depends only on the quantities and not on the order. Furthermore, we experimentally demonstrate that compared to previous methods, the nonlinear and commutative nature of DeCurvEd facilitates the disentanglement of image attributes and provides higher-quality editing.

In March, OpenAI sought to head off concerns that its immensely popular, albeit hallucination-prone, ChatGPT generative AI could be used to dangerously amplify political disinformation campaigns through an update to the company's Usage Policy to expressly prohibit such behavior. However, an investigation by The Washington Post shows that the chatbot is still easily incited to breaking those rules, with potentially grave repercussions for the 2024 election cycle. OpenAI's user policies specifically ban its use for political campaigning, save for use by "grassroots advocacy campaigns" organizations. This includes generating campaign materials in high volumes, targeting those materials at specific demographics, building campaign chatbots to disseminate information, engage in political advocacy or lobbying. Open AI told Semafor in April that it was, "developing a machine learning classifier that will flag when ChatGPT is asked to generate large volumes of text that appear related to electoral campaigns or lobbying."