A long-standing legal dispute to determine whether generative AI technologies can be named as the legal creators of their innovations has reached the highest court in the land, with a hearing at the UK Supreme Court on 2nd March 2023. A similar appeal hearing is underway at the US Supreme Court too. These hearings have been brought by a group of academics and inventors who believe that a generative AI system, called Dabus AI, is solely responsible for its own innovative outputs, two of which are the subject of patent applications filed in the UK, Europe and the US. These innovations include a novel interlocking food container that is easy for robots to handle, and a warning light or beacon that flickers in a rhythm similar to neural activity, which makes it difficult to ignore. Developed by Stephen Thaler in 1994, Dabus AI, also known as'The Creativity Machine', is a computational paradigm that claims to replicate human cognition.

Fifty-seven percent of U.S. adults believe "generative AI will make my daily life better," according to a new report by Dentsu. The survey of 1,000 online adults in the United States also found that 87% of consumers claim to have some awareness of generative AI, and 61% believe they at least somewhat understand the technology. Even more interesting is that 27% of U.S. adults say they have used generative AI, and another 42% are interested in trying the technology. These tremendously positive numbers seem to support the hyperbolic interest in ChatGPT and text-to-image generators such as Midjourney and Stable Diffusion. But, there is more to this story.

From fake photos of Donald Trump being arrested by New York City police officers to a chatbot describing a very-much-alive computer scientist as having died tragically, the ability of the new generation of generative artificial intelligence systems to create convincing but fictional text and images is setting off alarms about fraud and misinformation on steroids. Indeed, a group of artificial intelligence researchers and industry figures urged the industry on March 29, 2023, to pause further training of the latest AI technologies or, barring that, for governments to "impose a moratorium." These technologies – image generators like DALL-E, Midjourney and Stable Diffusion, and text generators like Bard, ChatGPT, Chinchilla and LLaMA – are now available to millions of people and don't require technical knowledge to use. Given the potential for widespread harm as technology companies roll out these AI systems and test them on the public, policymakers are faced with the task of determining whether and how to regulate the emerging technology. The Conversation asked three experts on technology policy to explain why regulating AI is such a challenge – and why it's so important to get it right.

Transformer networks have revolutionized NLP representation learning since they were introduced. Though a great effort has been made to explain the representation in transformers, it is widely recognized that our understanding is not sufficient. One important reason is that there lack enough visualization tools for detailed analysis. In this paper, we propose to use dictionary learning to open up these "black boxes" as linear superpositions of transformer factors. Through visualization, we demonstrate the hierarchical semantic structures captured by the transformer factors, e.g., word-level polysemy disambiguation, sentence-level pattern formation, and long-range dependency. While some of these patterns confirm the conventional prior linguistic knowledge, the rest are relatively unexpected, which may provide new insights. We hope this visualization tool can bring further knowledge and a better understanding of how transformer networks work. The code is available at https://github.com/zeyuyun1/TransformerVis

OpenAI has recently released GPT-4 (a.k.a. ChatGPT plus), which is demonstrated to be one small step for generative AI (GAI), but one giant leap for artificial general intelligence (AGI). Since its official release in November 2022, ChatGPT has quickly attracted numerous users with extensive media coverage. Such unprecedented attention has also motivated numerous researchers to investigate ChatGPT from various aspects. According to Google scholar, there are more than 500 articles with ChatGPT in their titles or mentioning it in their abstracts. Considering this, a review is urgently needed, and our work fills this gap. Overall, this work is the first to survey ChatGPT with a comprehensive review of its underlying technology, applications, and challenges. Moreover, we present an outlook on how ChatGPT might evolve to realize general-purpose AIGC (a.k.a. AI-generated content), which will be a significant milestone for the development of AGI.

Because of the inevitable cost and complexity of transformer and pre-trained models, efficiency concerns are raised for long text classification. Meanwhile, in the highly sensitive domains, e.g., healthcare and legal long-text mining, potential model distrust, yet underrated and underexplored, may hatch vital apprehension. Existing methods generally segment the long text, encode each piece with the pre-trained model, and use attention or RNNs to obtain long text representation for classification. In this work, we propose a simple but effective model, Segment-aWare multIdimensional PErceptron (SWIPE), to replace attention/RNNs in the above framework. Unlike prior efforts, SWIPE can effectively learn the label of the entire text with supervised training, while perceive the labels of the segments and estimate their contributions to the long-text labeling in an unsupervised manner. As a general classifier, SWIPE can endorse different encoders, and it outperforms SOTA models in terms of classification accuracy and model efficiency. It is noteworthy that SWIPE achieves superior interpretability to transparentize long text classification results.

While Huge amounts of unstructured, textual data are most of these studies did not feed the refinement operations generated daily. As more data becomes available, into an iterative retraining process, Smith it becomes more difficult to search, understand et al. (2018) implemented a fully interactive, usercentered and discover the knowledge within it. Because of HL-TM system, and examined how the the human effort it requires, conventional qualitative user experience is affected by issues arising in interactive approaches, such as Grounded Theory, (Glaser systems, such as unpredictability, trust and et al., 1968) are no longer feasible with such large lack of control. However, there are still limitations volumes of data. Topic modelling is a potential to their work. First, their system only allows users solution that has received increasing attention in to refine the model sequentially, meaning that once recent research (Heidenreich et al., 2019; Curiskis a user updates the model, a new model overrides et al., 2020; Dantu et al., 2021; Goyal and Howlett, the previous model. This prevents users from comparing 2021) to help users organize, search, and understand the effects of applying different refinement large amounts of information. It is an unsupervised operations to the same model, making it difficult machine learning technique for identifying to find the most appropriate ones.

Artificial intelligence (AI) systems can cause harm to people. This research examines how individuals react to such harm through the lens of blame. Building upon research suggesting that people blame AI systems, we investigated how several factors influence people's reactive attitudes towards machines, designers, and users. The results of three studies (N = 1,153) indicate differences in how blame is attributed to these actors. Whether AI systems were explainable did not impact blame directed at them, their developers, and their users. Considerations about fairness and harmfulness increased blame towards designers and users but had little to no effect on judgments of AI systems. Instead, what determined people's reactive attitudes towards machines was whether people thought blaming them would be a suitable response to algorithmic harm. We discuss implications, such as how future decisions about including AI systems in the social and moral spheres will shape laypeople's reactions to AI-caused harm.

With growing machine learning (ML) applications in healthcare, there have been calls for fairness in ML to understand and mitigate ethical concerns these systems may pose. Fairness has implications for global health in Africa, which already has inequitable power imbalances between the Global North and South. This paper seeks to explore fairness for global health, with Africa as a case study. We propose fairness attributes for consideration in the African context and delineate where they may come into play in different ML-enabled medical modalities. This work serves as a basis and call for action for furthering research into fairness in global health.

In the past few months, artificial intelligence has managed to pass the bar exam, create award-winning art, and diagnose sick patients better than most physicians. Soon it might eliminate millions of jobs. At least those are the arguments being made by its boosters and detractors in Silicon Valley. But Amba Kak, the executive director of the AI Now Institute, a New York–based group studying artificial intelligence's effects on society, says Americans should view the technology with neither a sense of mystery nor a feeling of awed resignation. The former Federal Trade Commission adviser thinks regulators need to analyze AI's consumer and business applications with a shrewd, empowered skepticism. Kak and I discussed how to understand AI, the risks it poses, whether the technology is overhyped, and how to regulate it. Our conversation has been condensed and edited for clarity.