Technology The U.S. Mint is auctioning the last pennies--and they could sell for millions Breakthroughs, discoveries, and DIY tips sent every weekday. In everyday transactions, a one cent penny is worth exactly its face value. But as any coin collector knows, some pennies are worth more than others. For example, a single mint-condition 1909 Lincoln wheat penny is currently valued at around $21, while an even rarer "Indian Head" penny from 1859 can sell for as much as $986. While it's unclear how much the very last pennies ever produced are worth, purchasing them at an upcoming auction will undoubtedly cost much more than pocket change.

Television is often seen as a site for subcultural identification and subversive fantasy, including in queer cultures. How might we measure subversion, or the degree to which the depiction of social relationship between a dyad (e.g. two characters who are colleagues) deviates from its typical representation on TV? To explore this question, we introduce the task of stereotypic relationship extraction. Built on cognitive stylistics, linguistic anthropology, and dialogue relation extraction, in this paper, we attempt to model the cognitive process of stereotyping TV characters in dialogic interactions. Given a dyad, we want to predict: what social relationship do the speakers exhibit through their words? Subversion is then characterized by the discrepancy between the distribution of the model's predictions and the ground truth labels. To demonstrate the usefulness of this task and gesture at a methodological intervention, we enclose four case studies to characterize the representation of queer relationalities in the Big Bang Theory, Frasier, and Gilmore Girls, as we explore the suspicious and reparative modes of reading with our computational methods.

Detecting critical moments, such as emotional outbursts or changes in decisions during conversations, is crucial for understanding shifts in human behavior and their consequences. Our work introduces a novel problem setting focusing on these moments as turning points (TPs), accompanied by a meticulously curated, high-consensus, human-annotated multi-modal dataset. We provide precise timestamps, descriptions, and visual-textual evidence high-lighting changes in emotions, behaviors, perspectives, and decisions at these turning points. We also propose a framework, TPMaven, utilizing state-of-the-art vision-language models to construct a narrative from the videos and large language models to classify and detect turning points in our multi-modal dataset. Evaluation results show that TPMaven achieves an F1-score of 0.88 in classification and 0.61 in detection, with additional explanations aligning with human expectations.

"In the end it was the data that killed me," says Penny* about her decision to leave the dating app Bumble. If she opened the app she might receive 100 likes, 25% of which she might be interested in. She would look at their profiles and write individualised messages; a few would respond, perhaps one would result in a date. "That's a lot of effort to get one date," she says. Bumble, billed as the feminist Tinder when it launched in 2014, this week announced it was taking action to relieve the administrative burden on its female users.

Extensive research exists on the performance of large language models on logic-based tasks, whereas relatively little has been done on their ability to generate creative solutions on lateral thinking tasks. The BrainTeaser shared task tests lateral thinking and uses adversarial datasets to prevent memorization, resulting in poor performance for out-of-the-box models. We propose a system for iterative, chain-of-thought prompt engineering which optimizes prompts using human evaluation. Using this shared task, we demonstrate our system's ability to significantly improve model performance by optimizing prompts and evaluate the input dataset.

In 2016, Oskarina Fuentes got a tip from a friend that seemed too good to be true. Her life in Venezuela had become a struggle: Inflation had hit 800 percent under President Nicolás Maduro, and the 26-year-old Fuentes had no stable job and was balancing multiple side hustles to survive. Her friend told her about Appen, an Australian data services company that was looking for crowdsourced workers to tag training data for artificial intelligence algorithms. Most internet users will have done some form of data labeling: identifying images of traffic lights and buses for online captchas. But the algorithms powering new bots that can pass legal exams, create fantastical imagery in seconds, or remove harmful content on social media are trained on datasets--images, video, and text--labeled by gig economy workers in some of the world's cheapest labor markets. Appen's clients have included Amazon, Facebook, Google, and Microsoft, and the company's 1 million contributors are just a part of a vast, hidden industry.

Modern large language models (LLMs) have demonstrated impressive capabilities at sophisticated tasks, often through step-by-step reasoning similar to humans. This is made possible by their strong few and zero-shot abilities -- they can effectively learn from a handful of handcrafted, completed responses ("in-context examples"), or are prompted to reason spontaneously through specially designed triggers. Nonetheless, some limitations have been observed. First, performance in the few-shot setting is sensitive to the choice of examples, whose design requires significant human effort. Moreover, given the diverse downstream tasks of LLMs, it may be difficult or laborious to handcraft per-task labels. Second, while the zero-shot setting does not require handcrafting, its performance is limited due to the lack of guidance to the LLMs. To address these limitations, we propose Consistency-based Self-adaptive Prompting (COSP), a novel prompt design method for LLMs. Requiring neither handcrafted responses nor ground-truth labels, COSP selects and builds the set of examples from the LLM zero-shot outputs via carefully designed criteria that combine consistency, diversity and repetition. In the zero-shot setting for three different LLMs, we show that using only LLM predictions, COSP improves performance up to 15% compared to zero-shot baselines and matches or exceeds few-shot baselines for a range of reasoning tasks.

A recent study conducted by the Department of Natural Resources has uncovered a startling link between forced prison labor in Louisiana and chemical pollution. According to the report, prison inmates are being used as a source of cheap labor to help companies produce pollutants that are then released into the environment. The report states that prisoners are being paid as little as $0.03 an hour to work in factories and refineries that produce hazardous materials. This is far below the minimum wage, and the prisoners are often not provided with the appropriate safety gear to protect themselves from the harmful chemicals. The study also found that the companies are not disposing of the hazardous waste properly, leading to contamination of water sources and air pollution.

Created by Penny de Byl, Jim Walsh, Penny @Holistic3D.com Strap yourself in: Programming Artificial Intelligence is about to click! Since making the official tutorials for Bolt on Unity's Learn Site, creating this course has been a dream of mine. In collaboration with Holistic3D, I took Penny's quintessential C# tutorial series The Beginner's Guide to Artificial Intelligence and adapted it to *drumroll*… Unity Visual Scripting! In this course, you're getting the best of both worlds: Learning content from a renowned expert on AI and computer science remixed, reconfigured, and riffed on by a creative artist and designer who has helped thousands learn visual scripting from the early years to today… that's me!

Our goal is a teachable reasoning system for question-answering (QA), where a user can interact with faithful answer explanations, and correct its errors so that the system improves over time. Our approach is to augment a QA model with a dynamic memory of user feedback, containing user-supplied corrections to erroneous model beliefs that users identify during interaction. Retrievals from memory are used as additional context for QA, to help avoid previous mistakes in similar new situations - a novel application of memory-based continuous learning. With simulated feedback, we find that our system (called TeachMe) continually improves with time, and without model retraining, requiring feedback on only 25% of training examples to reach within 1% of the upper-bound (feedback on all examples). Similarly, in experiments with real users, we observe a similar trend, with performance improving by over 15% on a hidden test set after teaching. This suggests new opportunities for using frozen language models in an interactive setting where users can inspect, debug, and correct the model's beliefs, leading to improved system's performance over time.