AI assistance in decision-making has become popular, yet people's inappropriate reliance on AI often leads to unsatisfactory human-AI collaboration performance. In this paper, through three pre-registered, randomized human subject experiments, we explore whether and how the provision of {second opinions} may affect decision-makers' behavior and performance in AI-assisted decision-making. We find that if both the AI model's decision recommendation and a second opinion are always presented together, decision-makers reduce their over-reliance on AI while increase their under-reliance on AI, regardless whether the second opinion is generated by a peer or another AI model. However, if decision-makers have the control to decide when to solicit a peer's second opinion, we find that their active solicitations of second opinions have the potential to mitigate over-reliance on AI without inducing increased under-reliance in some cases. We conclude by discussing the implications of our findings for promoting effective human-AI collaborations in decision-making.

More than 100 deepfake video advertisements impersonating Rishi Sunak were paid to be promoted on Facebook in the last month alone, according to research that has raised alarm about the risk AI poses before the general election. The adverts may have reached as many as 400,000 people – despite appearing to break several of Facebook's policies – and mark the first time that the prime minister's image has been doctored in a systematic way en masse. More than 12,929 was spent on 143 adverts, originating from 23 countries including the US, Turkey, Malaysia and the Philippines. They include one with faked footage of a BBC newsreader, Sarah Campbell, appearing to read out breaking news that falsely claims a scandal has erupted around Sunak secretly earning "colossal sums from a project that was initially intended for ordinary citizens". It carries the untrue claim that Elon Musk has launched an application capable of "collecting" stock market transactions and follows with a faked clip of Sunak saying the government had decided to test the application rather than risking the money of ordinary people.

B2 is a sleek, powerful robot that can run faster, jump higher and carry more weight than its predecessor, the B1. You may have heard of Boston Dynamics, the company that created the famous four-legged robot Spot. Well, now there is another company that is making impressive strides in the field of quadruped robotics. That company is Unitree, a Chinese start-up that has been developing its own line of robot dogs since 2016. Unitree's latest product is the B2, a sleek and powerful robot that can run faster, jump higher, and carry more weight than its predecessor, the B1.

The next year in technology is to be dominated by upgrades for everything from catflaps to binoculars to cars, devices that disappear in your home including transparent televisions, plus a new era of spatial computing brought in by some very expensive goggles. Those are the predictions from the annual CES tech show in Las Vegas that drew to a close this week. Unlike previous years, the event was not dominated by the big technology and car firms but rather a record-breaking 1,400 startups displaying their prototypes in hopes of catching the eyes of consumers and investors alike. Despite myriad promises to the contrary, many of these novel gadgets may never make it to the shops. But all of them show how technology is progressing and give a glimpse of what's next.

If your first thought, as we ushered in the New Year, was not of fresh starts and resolutions but of the crises looming in 2024 and beyond, the best antidote, culturally speaking, might be to lean into catastrophe. Metrograph has catered to the pessimists among us by curating a series entitled "The Future Looks Bright from Afar" (through Feb. 4), which promises a suite of sci-fi films marked by "grim prognostications" about mankind's trajectory. As it happens, the great new crowd-pleaser of the moment is also a disaster story, albeit one set firmly in the past. "Godzilla Minus One" follows a kamikaze pilot who shirks his duty in the final days of the Second World War--a decision that puts him in the path of the eponymous monster and, years later, leaves him uniquely motivated to stop its rampage through postwar Tokyo. Elevated by emotional and historical specificity as well as set pieces that belie its modest fifteen-million-dollar budget, Takashi Yamazaki's contribution to the Godzilla canon is simultaneously a study in survivor's guilt and a "Jaws"-style blockbuster, complete with the revelation that our protagonists are going to need a bigger boat.

A new ad featuring an AI-generated Taylor Swift offering a giveaway of high-end cookware is not the real deal. An ad for Le Creuset appeared on social media this month, featuring a likeness of Swift and a fake version of her voice with images of the company's cookware to promote a giveaway, according to multiple outlets. "Hey you all, it's Taylor Swift here," the voice says, according to NBC News. A spokesperson for Meta, Facebook's parent company, confirmed to Fox News Digital that the ad has been removed from the platform. WHAT IS ARTIFICIAL INTELLIGENCE (AI)? Taylor Swift's AI-generated likeness and voice were used in an unauthorized ad for cookware company Le Creuset.

The advent of instruction-tuned language models that convincingly mimic human writing poses a significant risk of abuse. For example, such models could be used for plagiarism, disinformation, spam, or phishing. However, such abuse may be counteracted with the ability to detect whether a piece of text was composed by a language model rather than a human. Some previous approaches to this problem have relied on supervised methods trained on corpora of confirmed human and machine-written documents. Unfortunately, model under-specification poses an unavoidable challenge for neural network-based detectors, making them brittle in the face of data shifts, such as the release of further language models producing still more fluent text than the models used to train the detectors. Other previous approaches require access to the models that may have generated a document in question at inference or detection time, which is often impractical. In light of these challenges, we pursue a fundamentally different approach not relying on samples from language models of concern at training time. Instead, we propose to leverage representations of writing style estimated from human-authored text. Indeed, we find that features effective at distinguishing among human authors are also effective at distinguishing human from machine authors, including state of the art large language models like Llama 2, ChatGPT, and GPT-4. Furthermore, given a handful of examples composed by each of several specific language models of interest, our approach affords the ability to predict which model generated a given document.

Hate speech represents a pervasive and detrimental form of online discourse, often manifested through an array of slurs, from hateful tweets to defamatory posts. As such speech proliferates, it connects people globally and poses significant social, psychological, and occasionally physical threats to targeted individuals and communities. Current computational linguistic approaches for tackling this phenomenon rely on labelled social media datasets for training. For unifying efforts, our study advances in the critical need for a comprehensive meta-collection, advocating for an extensive dataset to help counteract this problem effectively. We scrutinized over 60 datasets, selectively integrating those pertinent into MetaHate. This paper offers a detailed examination of existing collections, highlighting their strengths and limitations. Our findings contribute to a deeper understanding of the existing datasets, paving the way for training more robust and adaptable models. These enhanced models are essential for effectively combating the dynamic and complex nature of hate speech in the digital realm.

Large Language Models (LLMs) have demonstrated superior results across a wide range of tasks, while retrieval has long been established as an effective means of obtaining task-relevant information for humans. Retrieval-augmented Generation (RAG) are known for their effectiveness in knowledge-intensive tasks by locating relevant information and placing it within the context window of the LLM. However, the relationship between retrievers and LLMs is still under-investigated. Most existing work treats the retriever and the LLM as independent components and leaves a gap between retrieving human-friendly information and assembling a LLM-friendly context. In this work, we examine a novel bridge model, validate the ranking and selection assumptions in retrievers in the context of RAG, and propose a training framework that chains together supervised and reinforcement learning to learn a bridge model. Empirical results demonstrate the effectiveness of our method in both question-answering and personalized generation tasks.

Recent large language models (LLMs) have been shown to be effective for misinformation detection. However, the choice of LLMs for experiments varies widely, leading to uncertain conclusions. In particular, GPT-4 is known to be strong in this domain, but it is closed source, potentially expensive, and can show instability between different versions. Meanwhile, alternative LLMs have given mixed results. In this work, we show that Zephyr-7b presents a consistently viable alternative, overcoming key limitations of commonly used approaches like Llama-2 and GPT-3.5. This provides the research community with a solid open-source option and shows open-source models are gradually catching up on this task. We then highlight how GPT-3.5 exhibits unstable performance, such that this very widely used model could provide misleading results in misinformation detection. Finally, we validate new tools including approaches to structured output and the latest version of GPT-4 (Turbo), showing they do not compromise performance, thus unlocking them for future research and potentially enabling more complex pipelines for misinformation mitigation.