Amazon Prime Day is four days in 2025, and we've reached the final day. The Prime Day deals started dropping last month and end at midnight tonight (Friday, July 11). We have been working in shifts, covering 20 hours a day through the end, in a dangerously caffeinated state--all to help you nab the best Prime Day deals with up-to-date recommendations. The WIRED Reviews team only recommends deals on products we've tested and approved, and which are actually discounted. If you're looking for up-to-the-minute coverage of deals, check out our Amazon Prime Day liveblog, which will run from 5 am to midnight daily. If you're coming to Prime Day looking for something dirt-cheap, I've got one for you. Yes, this device is a Chromebook, but as a "Chromebook Plus" model, it's a big step up from the reputation these laptops have when kids are introduced to them in schools. The Acer Chromebook Plus 515 comes with a 1080p display, a spacious 15.6-inch display, and an Intel Core i3 processor.

Recommender systems powered by generative models (Gen-RecSys) extend beyond classical item ranking by producing open-ended content, which simultaneously unlocks richer user experiences and introduces new risks. On one hand, these systems can enhance personalization and appeal through dynamic explanations and multi-turn dialogues. On the other hand, they might venture into unknown territory-hallucinating nonexistent items, amplifying bias, or leaking private information. Traditional accuracy metrics cannot fully capture these challenges, as they fail to measure factual correctness, content safety, or alignment with user intent. This paper makes two main contributions. First, we categorize the evaluation challenges of Gen-RecSys into two groups: (i) existing concerns that are exacerbated by generative outputs (e.g., bias, privacy) and (ii) entirely new risks (e.g., item hallucinations, contradictory explanations). Second, we propose a holistic evaluation approach that includes scenario-based assessments and multi-metric checks-incorporating relevance, factual grounding, bias detection, and policy compliance. Our goal is to provide a guiding framework so researchers and practitioners can thoroughly assess Gen-RecSys, ensuring effective personalization and responsible deployment.

Explanations play a variety of roles in various recommender systems, from a legally mandated afterthought, through an integral element of user experience, to a key to persuasiveness. A natural and useful form of an explanation is the Counterfactual Explanation (CE). We present a method for generating highly plausible CEs in recommender systems and evaluate it both numerically and with a user study.

Traditional recommendation algorithms are not designed to provide personalized recommendations based on user preferences provided through text, e.g., "I enjoy light-hearted comedies with a lot of humor". Large Language Models (LLMs) have emerged as one of the most promising tools for natural language processing in recent years. This research proposes a novel framework that mimics how a close friend would recommend items based on their knowledge of an individual's tastes. We leverage LLMs to enhance movie recommendation systems by refining traditional algorithm outputs and integrating them with language-based user preference inputs. We employ Singular Value Decomposition (SVD) or SVD++ algorithms to generate initial movie recommendations, implemented using the Surprise Python library and trained on the MovieLens-Latest-Small dataset. We compare the performance of the base algorithms with our LLM-enhanced versions using leave-one-out validation hit rates and cumulative hit rates. Additionally, to compare the performance of our framework against the current state-of-the-art recommendation systems, we use rating and ranking metrics with an item-based stratified 0.75 train, 0.25 test split. Our framework can generate preference profiles automatically based on users' favorite movies or allow manual preference specification for more personalized results. Using an automated approach, our framework overwhelmingly surpassed SVD and SVD++ on every evaluation metric used (e.g., improvements of up to ~6x in cumulative hit rate, ~3.7x in NDCG, etc.), albeit at the cost of a slight increase in computational overhead.

The sale event of the summer is here, and the Amazon Prime Day Kindle deals (and other Amazon device deals!) are ones you can count on being great to shop. As someone who tests Amazon gear for a living--Echo speakers, Kindles, Amazon's smart plugs, you name it--I'm always tracking what in Amazon's lineup is worth buying. I have a ton of favorites, from the best of the best, like the Kindle Paperwhite and Echo Show 8, to the Kindle Scribe and Echo Spot. It's the perfect time to shop all of those and more. Not only is everything in this guide WIRED-tested and WIRED-approved, but it's on sale right now.

Amazon Prime Day is four days in 2025, and we're kicking off day three. The Prime Day deals started dropping last month and will end on Friday, July 11. We're working in shifts, covering 20 hours a day through the end, and are dangerously caffeinated--all to help you nab the best Prime Day deals with up-to-date recommendations. The WIRED Reviews team only recommends deals on products we've actually tested and approved, and which are actually discounted. If you're looking for up-to-the-minute coverage of deals, check out our Amazon Prime Day liveblog, which will run from 5 am to midnight daily. If you're coming to Prime Day looking for something dirt-cheap, I've got one for you. Yes, this device is a Chromebook, but as a "Chromebook Plus" model, it's a big step up from the reputation these laptops have when kids are introduced to them in schools. The Acer Chromebook Plus 515 comes with a 1080p display, a spacious 15.6-inch display, and an Intel Core i3 processor. Don't write off a ...

--Federated recommender systems (FedRec) have emerged as a promising solution for delivering personalized recommendations while safeguarding user privacy. However, recent studies have demonstrated their vulnerability to poisoning attacks, wherein adversarial clients can inject carefully crafted updates to manipulate global recommendations. Existing attacks typically target the entire user group, which compromises stealth and increases the risk of detection. In contrast, real-world adversaries may prefer to prompt target items to specific user subgroups, such as recommending health supplements to elderly users, in order to improve attack success rates while preserving stealth. Motivated by this gap, we introduce Spattack, the first targeted poisoning attack designed to manipulate recommendations for specific user subgroups in the federated setting. Specifically, Spattack adopts a two-stage approximation-and-promotion strategy, which first simulates user embeddings of target/non-target subgroups and then prompts target items to the target subgroups. T o enhance the approximation stage, we push the inter-group embeddings away based on contrastive learning and augment the target group's relevant item set based on clustering. T o enhance the promotion stage, we further propose to adaptively tune the optimization weights between target and non-target subgroups. Besides, an embedding alignment strategy is proposed to align the embeddings between the target items and the relevant items. We conduct comprehensive experiments on three real-world datasets, comparing Spattack against seven state-of-the-art poisoning attacks and seven representative defense mechanisms. Experimental results demonstrate that Spattack consistently achieves strong manipulation performance on the specific user subgroup, while incurring minimal impact on non-target users, even when only 0.1% of users are malicious. Moreover, Spattack maintains competitive overall recommendation performance and exhibits strong resilience against existing mainstream defenses.

The sale event of the summer is here, and the Amazon Prime Day Kindle deals (and other Amazon device deals!) are ones you can count on being great to shop. As someone who tests Amazon gear for a living--Echo speakers, Kindles, Amazon's smart plugs, you name it--I'm always tracking what in Amazon's lineup is worth buying. I have a ton of favorites, from the best of the best, like the Kindle Paperwhite and Echo Show 8, to the Kindle Scribe and Echo Spot. It's the perfect time to shop all of those and more. Not only is everything in this guide WIRED-tested and WIRED-approved, but it's on sale right now.

Amazon Prime Day began as one day and is now much more of an event, lasting four days this year. The Prime Day deals started dropping last month, and will go on through Friday. We'll be dangerously caffeinated and working in shifts, covering 20 hours a day through the end. The WIRED Reviews team only recommends deals on products we've actually tested and approved, and which are actually discounted. If you're looking for up-to-the-minute coverage of deals, check out our Amazon Prime Day liveblog, which will run from 5 am to midnight daily. Updated July 9, 2025: We've added over two dozen new deals on our favorite laptops, robot vacuums, TVs, security cameras, and more. If you want something hard-wearing and fast charging from the best USB-C cables, this is our pick. It tops out at 240 watts and has a tough, braided nylon exterior made from 100 percent recycled plastic. Anker promises this cable will last a century and it can operate in temperatures from -40 degrees to 176 degrees ...

LLM-powered applications are highly susceptible to the quality of user prompts, and crafting high-quality prompts can often be challenging especially for domain-specific applications. This paper presents a novel dynamic context-aware prompt recommendation system for domain-specific AI applications. Our solution combines contextual query analysis, retrieval-augmented knowledge grounding, hierarchical skill organization, and adaptive skill ranking to generate relevant and actionable prompt suggestions. The system leverages behavioral telemetry and a two-stage hierarchical reasoning process to dynamically select and rank relevant skills, and synthesizes prompts using both predefined and adaptive templates enhanced with few-shot learning. Experiments on real-world datasets demonstrate that our approach achieves high usefulness and relevance, as validated by both automated and expert evaluations.