The second season of Fallout - Prime Video's mega-hit based on the popular video game series - has landed. Set in a post-apocalyptic future where Earth has been ravaged by nuclear war, the first series was a commercial and critical hit, impressing long-time fans and viewers who'd never played before. Its surprising success had a huge impact on Bethesda Softworks, the developer of its source material, bringing back lapsed players and creating new ones along the way. Key creatives from the company have told BBC Newsbeat about working with the show's producers, and what the success of the programme means for the future of the games. The first season of Fallout arrived at a turning point for Hollywood video game adaptations.

Large language models show promise for embodying historical characters in dialogue systems, but existing approaches face a critical trade-off: simple retrieval-augmented generation produces shallow responses, while multi-stage reflection achieves depth at prohibitive latency. We present an architecture that resolves this tension through offline data augmentation and efficient parallel retrieval from structured episodic memory. Our system transforms biographical data into 1,774 enriched first-person memories with affective-semantic metadata, then employs two-stage retrieval achieving 0.52s prompt generation. Evaluation using LLM-as-judge and RAGAs metrics shows our approach achieves parity with traditional RAG on GPT-4 while significantly outperforming it on smaller models (GPT-3.5, GPT-3), suggesting particular value for resource-constrained deployments. Beyond dialogue, the structured memory enables novel visualization tools: spatiotemporal heatmaps, emotional trajectory analysis, and interactive path tracking, positioning the system as both a dialogue interface and research tool for biographical analysis. We use Van Gogh as a test case, but the architecture is generalizable to any historical figure with substantial textual records, offering a practical framework for educational, museum, and research applications requiring both accuracy and efficiency

This paper analyses AI-generated podcasts produced by Google's NotebookLM, which generates audio podcasts with two chatty AI hosts discussing whichever documents a user uploads. While AI-generated podcasts have been discussed as tools, for instance in medical education, they have not yet been analysed as media. By uploading different types of text and analysing the generated outputs I show how the podcasts' structure is built around a fixed template. I also find that NotebookLM not only translates texts from other languages into a perky standardised Mid-Western American accent, it also translates cultural contexts to a white, educated, middle-class American default. This is a distinct development in how publics are shaped by media, marking a departure from the multiple public spheres that scholars have described in human podcasting from the early 2000s until today, where hosts spoke to specific communities and responded to listener comments, to an abstraction of the podcast genre.

The proliferation of scientific literature presents an increasingly significant challenge for researchers. While Large Language Models (LLMs) offer promise, existing tools often provide verbose summaries that risk replacing, rather than assisting, the reading of the source material. This paper introduces InsightGUIDE, a novel AI-powered tool designed to function as a reading assistant, not a replacement. Our system provides concise, structured insights that act as a "map" to a paper's key elements by embedding an expert's reading methodology directly into its core AI logic. We present the system's architecture, its prompt-driven methodology, and a qualitative case study comparing its output to a general-purpose LLM. The results demonstrate that InsightGUIDE produces more structured and actionable guidance, serving as a more effective tool for the modern researcher.

A Whole Slide Image (WSI) is a high-resolution digital image created by scanning an entire glass slide containing a biological specimen, such as tissue sections or cell samples, at multiple magnifications. These images can be viewed, analyzed, shared digitally, and are used today for Artificial Intelligence (AI) algorithm development. WSIs are used in a variety of fields, including pathology for diagnosing diseases and oncology for cancer research. They are also utilized in neurology, veterinary medicine, hematology, microbiology, dermatology, pharmacology, toxicology, immunology, and forensic science. When assembling cohorts for the training or validation of an AI algorithm, it is essential to know what is present on such a WSI. However, there is currently no standard for this metadata, so such selection has mainly been done through manual inspection, which is not suitable for large collections with several million objects. We propose a general framework to generate a 2D index map for WSI and a profiling mechanism for specific application domains. We demonstrate this approach in the field of clinical pathology, using common syntax and semantics to achieve interoperability between different catalogs. Our approach augments each WSI collection with a detailed tissue map that provides fine-grained information about the WSI content. The tissue map is organized into three layers: source, tissue type, and pathological alterations, with each layer assigning segments of the WSI to specific classes. We illustrate the advantages and applicability of the proposed standard through specific examples in WSI catalogs, Machine Learning (ML), and graph-based WSI representations.

We introduce a novel technique for creative audio resynthesis that operates by reworking the concept of granular synthesis at the latent vector level. Our approach creates a "granular codebook" by encoding a source audio corpus into latent vector segments, then matches each latent grain of a target audio signal to its closest counterpart in the codebook. The resulting hybrid sequence is decoded to produce audio that preserves the target's temporal structure while adopting the source's timbral characteristics. This technique requires no model training, works with diverse audio materials, and naturally avoids the discontinuities typical of traditional concatenative synthesis through the codec's implicit interpolation during decoding. We include supplementary material at https://github.com/naotokui/latentgranular/ , as well as a proof-of-concept implementation to allow users to experiment with their own sounds at https://huggingface.co/spaces/naotokui/latentgranular .

Even when instructed to adhere to source material, Language Models often generate unsubstantiated content - a phenomenon known as "closed-domain hallucination." This risk is amplified in processes with multiple generative steps (MGS), compared to processes with a single generative step (SGS). However, due to the greater complexity of MGS processes, we argue that detecting hallucinations in their final outputs is necessary but not sufficient: it is equally important to trace where hallucinated content was likely introduced and how faithful content may have been derived from the source through intermediate outputs. To address this need, we present VeriTrail, the first closed-domain hallucination detection method designed to provide traceability for both MGS and SGS processes. We also introduce the first datasets to include all intermediate outputs as well as human annotations of final outputs' faithfulness for their respective MGS processes. We demonstrate that VeriTrail outperforms baseline methods on both datasets.

In high-stakes domains like legal question-answering, the accuracy and trustworthiness of generative AI systems are of paramount importance. This work presents a comprehensive benchmark of various methods to assess the groundedness of AI-generated responses, aiming to significantly enhance their reliability. Our experiments include similarity-based metrics and natural language inference models to evaluate whether responses are well-founded in the given contexts. We also explore different prompting strategies for large language models to improve the detection of ungrounded responses. We validated the effectiveness of these methods using a newly created grounding classification corpus, designed specifically for legal queries and corresponding responses from retrieval-augmented prompting, focusing on their alignment with source material. Our results indicate potential in groundedness classification of generated responses, with the best method achieving a macro-F1 score of 0.8. Additionally, we evaluated the methods in terms of their latency to determine their suitability for real-world applications, as this step typically follows the generation process. This capability is essential for processes that may trigger additional manual verification or automated response regeneration. In summary, this study demonstrates the potential of various detection methods to improve the trustworthiness of generative AI in legal settings.

For more than a decade, blockbuster comic book adaptations reliably clobbered all competition at the box office. Disney and HBO Max built their streaming strategies around intellectual property from Marvel and DC Comics. The studios turned this pulpy source material into a profusion of interconnected films and series that consistently drove ticket sales and subscriptions--until they didn't. Lately, serious superhero fatigue seems to have set in. Comic book movies regularly tank these days, and not just the ones based on second-string characters like Blue Beetle and Madame Web.

For decades, it seemed like Hollywood couldn't get a video game adaptation right. Movies like Double Dragon, Super Mario Bros., and Lara Croft: Tomb Raider were all critically panned, with their creators called out for either sticking too close to the source material, failing to capture the magic of the games, or casting actors who didn't really embrace the films' inherent campiness. In recent years, though, there's been a shift in game adaptations, with projects like The Last of Us and Werewolves Within achieving critical acclaim and--in the case of the former, at least--a boatload of awards nods. You could point to a number of reasons to try to explain why game adaptations are getting better (Pedro Pascal, for example), but Jonathan Nolan, co-creator of Amazon Prime Video's new series Fallout, says he thinks it's because games often have "more sophisticated, more interesting, and more daring" storytelling than is often found in film or TV. When Nolan first started playing Fallout 3 in 2009, while trying to write The Dark Knight Rises, he was taken aback.