A shared language for product teams to build usable, intelligent and safe GenAI experiences beyond just the modelGenerative AI introduces a new way for humans to interact with systems by focusing on intent-based outcome specification. GenAI introduces novel challenges because its outputs are probabilistic, requires understanding of variability, memory, errors, hallucinations and malicious use which brings an essential need to build principles and design patterns as described by IBM.Moreover, any AI product is a layered system where LLM is just one ingredient and memory, orchestration, tool extensions, UX and agentic user-flows builds the real magic!This article is my research and documentation of evolving GenAI design patterns that provide a shared language for product managers, data scientists, and interaction designers to create products that are human-centred, trustworthy and safe. By applying these patterns, we can bridge the gap between user needs, technical capabilities and product development process.Here are 21 GenAI UX patternsGenAI or no GenAIConvert user needs to data needsAugment or automateDefine level of automationProgressive AI adoptionLeverage mental modelsConvey product limitsDisplay chain of thought (CoT)Leverage multiple outputsProvide data sourcesConvey model confidenceDesign for memory and recallProvide contextual input parametersDesign for coPilot, co-Editing or partial automationDefine user controls for AutomationDesign for user input error statesDesign for AI system error statesDesign to capture user feedbackDesign for model evaluationDesign for AI safety guardrailsCommunicate data privacy and controls1. GenAI or no GenAIEvaluate whether GenAI improves UX or introduces complexity. Often, heuristic-based (IF/Else) solutions are easier to build and maintain.Scenarios when GenAI is beneficialTasks that are open-ended, creative and augments user.E.g., writing prompts, summarizing notes, drafting replies.Creating or transforming complex outputs (e.g., images, video, code).E.g., converting a sketch into website code.Where structured UX fails to capture user intent.Scenarios when GenAI should be avoidedOutcomes that must be precise, auditable or deterministic. E.g., Tax forms or legal contracts.Users expect clear and consistent information.E.g. Open source software documentationHow to use this patternDetermine the friction points in the customer journeyAssess technology feasibility: Determine if AI can address the friction point. Evaluate scale, dataset availability, error risk assessment and economic ROI.Validate user expectations: - Determine if the AI solution erodes user expectations by evaluating whether the system augments human effort or replaces it entirely, as outlined in pattern 3, Augment vs. automate. - Determine if AI solution erodes pattern 6, Mental models2. Convert user needs to data needsThis pattern ensures GenAI development begins with user intent and data model required to achieve that. GenAI systems are only as good as the data they’re trained on. But real users don’t speak in rows and columns, they express goals, frustrations, and behaviours. If teams fail to translate user needs into structured, model-ready inputs, the resulting system or product may optimise for the wrong outcomes and thus user churn.How to use this patternCollaborate as a cross-functional team of PMs, Product designers and Data Scientists and align on user problems worth solving.Define user needs by using triangulated research: Qualitative (Market Reports, Surveys or Questionnaires) + Quantitative (User Interviews, Observational studies) + Emergent (Product reviews, Social listening etc.) and synthesising user insights using JTBD framework, Empathy Map to visualise user emotions and perspectives. Value Proposition Canvas to align user gains and pains with featuresDefine data needs and documentation by selecting a suitable data model, perform gap analysis and iteratively refine data model as needed. Once you understand the why, translate it into the what for the model. What features, labels, examples, and contexts will your AI model need to learn this behaviour? Use structured collaboration to figure out.3. Augment vs automateOne of the critical decisions in GenAI apps is whether to fully automate a task or to augment human capability. Use this pattern to to align with user intent and control preferences with the technology.Automation is best for tasks users prefer to delegate especially when they are tedious, time-consuming or unsafe. E.g., Intercom FinAI automatically summarizes long email threads into internal notes, saving time on repetitive, low-value tasks.Augmentation enhances tasks users want to remain involved in by increasing efficiency, increase creativity and control. E.g., Magenta Studio in Abelton support creative controls to manipulate and create new music.How to use this patternTo select the best approach, evaluate user needs and expectations using research synthesis tools like empathy map (visualise user emotions and perspectives) and value proposition canvas (to understand user gains and pains)Test and validate if the approach erodes user experience or enhances it.4. Define level of automationIn AI systems, automation refers to how much control is delegated to the AI vs user. This is a strategic UX pattern to decide degree of automation based upon user pain-point, context scenarios and expectation from the product.Levels of automationNo automation (AI assists but user decides)The AI system provides assistance and suggestions to the user but requires the user to make all the decisions. E.g., Grammarly highlights grammar issues but the user accepts or rejects corrections.Partial automation/ co-pilot/ co-editor (AI acts with user oversight)The AI initiates actions or generates content, but the user reviews or intervenes as needed. E.g., GitHub Copilot suggest code that developers can accept, modify, or ignore.Full automation (AI acts independently)The AI system performs tasks without user intervention, often based on predefined rules, tools and triggers. Full automation in GenAI are often referred to as Agentic systems. E.g., Ema can autonomously plan and execute multi-step tasks like researching competitors, generating a report and emailing it without user prompts or intervention at each step.How to use this patternEvaluate user pain point to be automated and risk involved: Automating tasks is most effective when the associated risk is low without severe consequences in case of failure. Low-risk tasks such as sending automated reminders, promotional emails, filtering spam emails or processing routine customer queries can be automated with minimal downside while saving time and resources. High-risk tasks such as making medical diagnoses, sending business-critical emails, or executing financial trades requires careful oversight due to the potential for significant harm if errors occur.Evaluate and design for particular automation level: Evaluate if user pain point should fall under — No Automation, Partial Automation or Full Automation based upon user expectations and goals.Define user controls for automation (refer pattern 15)5. Progressive GenAI adoptionWhen users first encounter a product built on new technology, they often wonder what the system can and can’t do, how it works and how they should interact with it.This pattern offers multi-dimensional strategy to help user onboard an AI product or feature, mitigate errors, aligns with user readiness to deliver an informed and human-centered UX.How to use this patternThis pattern is a culmination of many other patternsFocus on communicating benefits from the start: Avoid diving into details about the technology and highlight how the AI brings new value.Simplify the onboarding experience Let users experience the system’s value before asking data-sharing preferences, give instant access to basic AI features first. Encourage users to sign up later to unlock advanced AI features or share more details. E.g., Adobe FireFly progressively onboards user with basic to advance AI featuresDefine level of automation (refer pattern 4) and gradually increase autonomy or complexity.Provide explainability and trust by designing for errors (refer pattern 16 and 17).Communicate data privacy and controls (refer pattern 21) to clearly convey how user data is collected, stored, processed and protected.6. Leverage mental modelsMental models help user predict how a system (web, application or other kind of product) will work and, therefore, influence how they interact with an interface. When a product aligns with a user’s existing mental models, it feels intuitive and easy to adopt. When it clashes, it can cause frustration, confusion, or abandonment​.E.g. Github Copilot builds upon developers’ mental models from traditional code autocomplete, easing the transition to AI-powered code suggestionsE.g. Adobe Photoshop builds upon the familiar approach of extending an image using rectangular controls by integrating its Generative Fill feature, which intelligently fills the newly created space.How to use this patternIdentifying and build upon existing mental models by questioningWhat is the user journey and what is user trying to do?What mental models might already be in place?Does this product break any intuitive patterns of cause and effect?Are you breaking an existing mental model? If yes, clearly explain how and why. Good onboarding, microcopy, and visual cues can help bridge the gap.7. Convey product limitsThis pattern involves clearly conveying what an AI model can and cannot do, including its knowledge boundaries, capabilities and limitations.It is helpful to builds user trust, sets appropriate expectations, prevents misuse, and reduces frustration when the model fails or behaves unexpectedly.How to use this patternExplicitly state model limitations: Show contextual cues for outdated knowledge or lack of real-time data. E.g., Claude states its knowledge cutoff when the question falls outside its knowledge domainProvide fallbacks or escalation options when the model cannot provide a suitable output. E.g., Amazon Rufus when asked about something unrelated to shopping, says “it doesn’t have access to factual information and, I can only assists with shopping related questions and requests”Make limitations visible in product marketing, onboarding, tooltips or response disclaimers.8. Display chain of thought (CoT)In AI systems, chain-of-thought (CoT) prompting technique enhances the model’s ability to solve complex problems by mimicking a more structured, step-by-step thought process like that of a human.CoT display is a UX pattern that improves transparency by revealing how the AI arrived at its conclusions. This fosters user trust, supports interpretability, and opens up space for user feedback especially in high-stakes or ambiguous scenarios.E.g., Perplexity enhances transparency by displaying its processing steps helping users understand the thoughtful process behind the answers.E.g., Khanmigo an AI Tutoring system guides students step-by-step through problems, mimicking human reasoning to enhance understanding and learning.How to use this patternShow status like “researching” and “reasoning to communicate progress, reduce user uncertainty and wait times feel shorter.Use progressive disclosure: Start with a high-level summary, and allow users to expand details as needed.Provide AI tooling transparency: Clearly display external tools and data sources the AI uses to generate recommendations.Show confidence & uncertainty: Indicate AI confidence levels and highlight uncertainties when relevant.9. Leverage multiple outputsGenAI can produce varied responses to the same input due to its probabilistic nature. This pattern exploits variability by presenting multiple outputs side by side. Showing diverse options helps users creatively explore, compare, refine or make better decisions that best aligns with their intent. E.g., Google Gemini provides multiple options to help user explore, refine and make better decisions.How to use this patternExplain the purpose of variation: Help users understand that differences across outputs are intentional and meant to offer choice.Enable edits: Let users rate, select, remix, or edit outputs seamlessly to shape outcomes and provide feedback. E.g., Midjourney helps user adjust prompt and guide your variations and edits using remix10. Provide data sourcesArticulating data sources in a GenAI application is essential for transparency, credibility and user trust. Clearly indicating where the AI derives its knowledge helps users assess the reliability of responses and avoid misinformation.This is especially important in high stakes factual domains like healthcare, finance or legal guidance where decisions must be based on verified data.How to use this patternCite credible sources inline: Display sources as footnotes, tooltips, or collapsible links. E.g., NoteBookLM adds citations to its answers and links each answer directly to the part of user’s uploaded documents.Disclose training data scope clearly: For generative tools (text, images, code), offer a simple explanation of what data the model was trained on and what wasn’t included. E.g., Adobe Firefly discloses that its Generative Fill feature is trained on stock imagery, openly licensed work and public domain content where the copyright has expired.Provide source-level confidence:In cases where multiple sources contribute, visually differentiate higher-confidence or more authoritative sources.11. Convey model confidenceAI-generated outputs are probabilistic and can vary in accuracy. Showing confidence scores communicates how certain the model is about its output. This helps users assess reliability and make better-informed decisions.How to use this patternAssess context and decision stakes: Showing model confidence depends on the context and its impact on user decision-making. In high-stakes scenarios like healthcare, finance or legal advice, displaying confidence scores are crucial. However, in low stake scenarios like AI-generated art or storytelling confidence may not add much value and could even introduce unnecessary confusion.Choose the right visualization: If design research shows that displaying model confidence aids decision-making, the next step is to select the right visualization method. Percentages, progress bars or verbal qualifiers (“likely,” “uncertain”) can communicate confidence effectively. The apt visualisation method depends on the application’s use-case and user familiarity. E.g., Grammarly uses verbal qualifiers like “likely” to the content it generated along with the userGuide user action during low confidence scenarios: Offer paths forward such as asking clarifying questions or offering alternative options.12. Design for memory and recallMemory and recall is an important concept and design pattern that enables the AI product to store and reuse information from past interactions such as user preferences, feedback, goals or task history to improve continuity and context awareness.Enhances personalization by remembering past choices or preferencesReduces user burden by avoiding repeated input requests especially in multi-step or long-form tasksSupports complex tasks like longitudinal workflows like in project planning, learning journeys by referencing or building on past progress.Memory used to access information can be ephemeral (short-term within a session) or persistent (long-term across sessions) and may include conversational context, behavioural signals, or explicit inputs.How to use this patternDefine the user context and choose memory typeChoose memory type like ephemeral or persistent or both based upon use case. A shopping assistant might track interactions in real time without needing to persist data for future sessions whereas personal assistants need long-term memory for personalization.Use memory intelligently in user interactionsBuild base prompts for LLM to recall and communicate information contextually (E.g., “Last time you preferred a lighter tone. Should I continue with that?”).Communicate transparency and provide controlsClearly communicate what’s being saved and let users view, edit or delete stored memory. Make “delete memories” an accessible action. E.g. ChatGPT offers extensive controls across it’s platform to view, update, or delete memories anytime.13. Provide contextual input parametersContextual Input parameters enhance the user experience by streamlining user interactions and gets to user goal faster. By leveraging user-specific data, user preferences or past interactions or even data from other users who have similar preferences, GenAI system can tailor inputs and functionalities to better meet user intent and decision making.How to use this patternLeverage prior interactions: Pre-fill inputs based on what the user has previously entered. Refer pattern 12, Memory and recall.Use auto complete or smart defaults: As users type, offer intelligent, real-time suggestions derived from personal and global usage patterns. E.g., Perplexity offers smart next query suggestions based on your current query thread.Suggest interactive UI widgets: Based upon system prediction, provide tailored input widgets like toasts, sliders, checkboxes to enhance user input. E.g., ElevenLabs allows users to fine-tune voice generation settings by surfacing presets or defaults.14. Design for co-pilot / co-editing / partial automationCo-pilot is an augmentation pattern where AI acts as a collaborative assistant, offering contextual and data-driven insights while the user remains in control. This design pattern is essential in domains like strategy, ideating, writing, designing or coding where outcomes are subjective, users have unique preferences or creative input from the user is critical.Co-pilot speed up workflows, enhance creativity and reduce cognitive load but the human retains authorship and final decision-making.How to use this patternEmbed inline assistance: Place AI suggestions contextually so users can easily accept, reject or modify them. E.g., Notion AI helps you draft, summarise and edit content while you control the final version.Save user intent and creative direction: Let users guide the AI with input like goals, tone, or examples, maintaining authorship and creative direction. E.g., Jasper AI allows users to set brand voice and tone guidelines, helping structure AI output to better match the user’s intent.15. Design user controls for automationBuild UI-level mechanisms that let users manage or override automation based upon user goals, context scenarios or system failure states.No system can anticipate all user contexts. Controls give users agency and keep trust intact even when the AI gets it wrong.How to use this patternUse progressive disclosure: Start with minimal automation and allow users to opt into more complex or autonomous features over time. E.g., Canva Magic Studio starts with simple AI suggestions like text or image generation then gradually reveals advanced tools like Magic Write, AI video scenes and brand voice customisation.Give users automation controls: UI controls like toggles, sliders, or rule-based settings to let users choose when and how automation can be controlled. E.g., Gmail lets users disable Smart Compose.Design for automation error recovery: Give users correction when AI fails (false positives/negatives). Add manual override, undo, or escalate options to human support. E.g., GitHub Copilot suggests code inline, but developers can easily reject, modify or undo suggestions when output is off.16. Design for user input error statesGenAI systems often rely on interpreting human input. When users provide ambiguous, incomplete or erroneous information, the AI may misunderstand their intent or produce low-quality outputs.Input errors often reflect a mismatch between user expectations and system understanding. Addressing these gracefully is essential to maintain trust and ensure smooth interaction.How to use this patternHandle typos with grace: Use spell-checking or fuzzy matching to auto-correct common input errors when confidence is high (e.g., >80%), and subtly surface corrections (“Showing results for…”).Ask clarifying questions: When input is too vague or has multiple interpretations, prompt the user to provide missing context. In Conversation Design, these types of errors occur when the intent is defined but the entity is not clear. Know more about entity and intent. E.g., ChatGPT when given low-context prompts like “What’s the capital?”, it asks follow-up questions rather than guessing.Support quick correction: Make it easy for users to edit or override your interpretation. E.g., ChatGPT displays an edit button beside submitted prompts, enabling users to revise their input17. Design for AI system error statesGenAI outputs are inherently probabilistic and subject to errors ranging from hallucinations and bias to contextual misalignments.Unlike traditional systems, GenAI error states are hard to predict. Designing for these states requires transparency, recovery mechanisms and user agency. A well-designed error state can help users understand AI system boundaries and regain control.A Confusion matrix helps analyse AI system errors and provides insight into how well the model is performing by showing the counts of - True positives (correctly identifying a positive case) - False positives (incorrectly identifying a positive case) - True negatives (correctly identifying a negative case)- False negatives (failing to identify a negative case)Scenarios of AI errors and failure statesSystem failure (wrong output)False positives or false negatives occur due to poor data, biases or model hallucinations. E.g., Citibank financial fraud system displays a message “Unusual transaction. Your card is blocked. If it was you, please verify your identity”System limitation errors (no output)True negatives occur due to untrained use cases or gaps in knowledge. E.g., when an ODQA system is given a user input outside the trained dataset, throws the following error “Sorry, we don’t have enough information. Please try a different query!”Contextual errors (misunderstood output)True positives that confuse users due to poor explanations or conflicts with user expectations comes under contextual errors. E.g., when user logs in from a new device, gets locked out. AI responds: “Your login attempt was flagged for suspicious activity”How to use this patternCommunicate AI errors for various scenarios: Use phrases like “This may not be accurate”, “This seems like…” or surface confidence levels to help calibrate trust.Use pattern convey model confidence for low confidence outputs.Offer error recovery: Incase of System failure or Contextual errors, provide clear paths to override, retry or escalate the issue. E.g., Use way forwards like “Try a different query,” or “Let me refine that.” or “Contact Support”.Enable user feedback: Make it easy to report hallucinations or incorrect outputs. Read more about pattern 19. Design to capture user feedback.18. Design to capture user feedbackReal-world alignment needs direct user feedback to improve the model and thus the product. As people interact with AI systems, their behaviours shape and influence the outputs they receive in the future. Thus, creating a continuous feedback loop where both the system and user behaviour adapt over time. E.g., ChatGPT uses Reaction buttons and Comment boxes to collect user feedback.How to use this patternAccount for implicit feedback: Capture user actions such as skips, dismissals, edits, or interaction frequency. These passive signals provide valuable behavioral cues that can tune recommendations or surface patterns of disinterest.Ask for explicit feedback: Collect direct user input through thumbs-up/down, NPS rating widgets or quick surveys after actions. Use this to improve both model behavior and product fit.Communicate how feedback is used: Let users know how their feedback shapes future experiences. This increases trust and encourages ongoing contribution.19. Design for model evaluationRobust GenAI models require continuous evaluation during training as well as post-deployment. Evaluation ensures the model performs as intended, identify errors and hallucinations and aligns with user goals especially in high-stakes domains.How to use this patternThere are three key evaluation methods to improve ML systems.LLM based evaluations (LLM-as-a-judge) A separate language model acts as an automated judge. It can grade responses, explain its reasoning and assign labels like helpful/harmful or correct/incorrect.E.g., Amazon Bedrock uses the LLM-as-a-Judge approach to evaluate AI model outputs.A separate trusted LLM, like Claude 3 or Amazon Titan, automatically reviews and rates responses based on helpfulness, accuracy, relevance, and safety. For instance, two AI-generated replies to the same prompt are compared, and the judge model selects the better one.This automation reduces evaluation costs by up to 98% and speeds up model selection without relying on slow, expensive human reviews.Enable code-based evaluations: For structured tasks, use test suites or known outputs to validate model performance, especially for data processing, generation, or retrieval.Capture human evaluation: Integrate real-time UI mechanisms for users to label outputs as helpful, harmful, incorrect, or unclear. Read more about it in pattern 19. Design to capture user feedbackA hybrid approach of LLM-as-a-judge and human evaluation drastically boost accuracy to 99%.20. Design for AI guardrailsDesign for AI guardrails means building practises and principles in GenAI models to minimise harm, misinformation, toxic behaviour and biases. It is a critical consideration toProtect users and children from harmful language, made-up facts, biases or false information.Build trust and adoption: When users know the system avoids hate speech and misinformation, they feel safer and show willingness to use it often.Ethical compliance: New rules like the EU AI act demand safe AI design. Teams must meet these standards to stay legal and socially responsible.How to use this patternAnalyse and guide user inputs: If a prompt could lead to unsafe or sensitive content, guide users towards safer interactions. E.g., when Miko robot comes across profanity, it answers“I am not allowed to entertain such language”Filter outputs and moderate content: Use real-time moderation to detect and filter potentially harmful AI outputs, blocking or reframing them before they’re shown to the user. E.g., show a note like: “This response was modified to follow our safety guidelines.Use pro-active warnings: Subtly notify users when they approach sensitive or high stakes information. E.g., “This is informational advice and not a substitute for medical guidance.”Create strong user feedback: Make it easy for users to report unsafe, biased or hallucinated outputs to directly improve the AI over time through active learning loops. E.g., Instagram provides in-app option for users to report harm, bias or misinformation.Cross-validate critical information: For high-stakes domains (like healthcare, law, finance), back up AI-generated outputs with trusted databases to catch hallucinations. Refer pattern 10, Provide data sources.21. Communicate data privacy and controlsThis pattern ensures GenAI applications clearly convey how user data is collected, stored, processed and protected.GenAI systems often rely on sensitive, contextual, or behavioral data. Mishandling this data can lead to user distrust, legal risk or unintended misuse. Clear communication around privacy safeguards helps users feel safe, respected and in control. E.g., Slack AI clearly communicates that customer data remains owned and controlled by the customer and is not used to train Slack’s or any third-party AI modelsHow to use this patternShow transparency: When a GenAI feature accesses user data, display explanation of what’s being accessed and why.Design opt-in and opt-out flows: Allow users to easily toggle data sharing preferences.Enable data review and deletion: Allow users to view, download or delete their data history giving them ongoing control.ConclusionThese GenAI UX patterns are a starting point and represent the outcome of months of research, shaped directly and indirectly with insights from notable designers, researchers, and technologists across leading tech companies and the broader AI communites across Medium and Linkedin. I have done my best to cite and acknowledge contributors along the way but I’m sure I’ve missed many. If you see something that should be credited or expanded, please reach out.Moreover, these patterns are meant to grow and evolve as we learn more about creating AI that’s trustworthy and puts people first. If you’re a designer, researcher, or builder working with AI, take these patterns, challenge them, remix them and contribute your own. Also, please let me know in comments about your suggestions. If you would like to collaborate with me to further refine this, please reach out to me.20+ GenAI UX patterns, examples and implementation tactics was originally published in UX Collective on Medium, where people are continuing the conversation by highlighting and responding to this story.

Researchers across Taiwan are tackling complex challenges in AI development, climate science and quantum computing. Their work will soon be boosted by a new supercomputer at Taiwan’s National Center for High-Performance Computing that’s set to deliver over 8x more AI performance than the center’s earlier Taiwania 2 system. The AI supercomputer at NCHC is slated to feature NVIDIA HGX H200 systems with over 1,700 GPUs, two NVIDIA GB200 NVL72 rack-scale systems and an NVIDIA HGX B300 system built on the NVIDIA Blackwell Ultra platform — interconnected by NVIDIA Quantum InfiniBand networking. Announced today at COMPUTEX, it’s expected to go live later this year. NCHC also plans to deploy a set of NVIDIA DGX Spark personal AI supercomputers and a cluster of NVIDIA HGX systems in the cloud. Researchers from academic institutions, government agencies and small businesses in Taiwan will be able to apply for access to the new system to accelerate innovative projects. “The new NCHC supercomputer will drive breakthroughs in sovereign AI, quantum computing and advanced scientific computation,” said Chau-Lyan Chang, director general of NCHC. “It’s designed to empower Taiwan’s technological autonomy, fostering cross-domain collaboration and global AI leadership.” Developing Local Language Models for Sovereign AI The new supercomputer will support projects like Taiwan AI RAP, a generative AI application development platform. Taiwan AI RAP aims to support the rapid development of AI products by offering startups, researchers and enterprises access to customized models that reflect local cultural and linguistic nuances. Among the platform’s offerings are models created by Taiwan’s Trustworthy AI Dialogue Engine, or TAIDE — a public sector initiative to build Taiwanese large language models (LLMs) for tasks including natural language processing, intelligent customer service and translation. Collaborators providing text, images, audio and video data for the initiative include local governments, news organizations and public departments such as the Ministry of Education and Ministry of Culture. To support the creation of sovereign AI applications, TAIDE currently offers developers access to a collection of Llama3.1-TAIDE foundation models. The team is building additional sovereign AI LLM services using NVIDIA Nemotron models. A professor at National Tainan University is using the TAIDE model to power a conversational AI robot that speaks Taiwanese and English with elementary and middle school students. It’s been used by over 2,000 students, teachers and parents to date. Another professor tapped the model to generate high-quality educational materials, shortening lesson preparation time for teachers. In healthcare, research teams in Taiwan used the TAIDE model to develop an AI chatbot with retrieval-augmented generation that helps case managers deliver timely, accurate medical information to patients with major injuries and illnesses. And the Epidemic Prevention Center at Taiwan’s Centers for Disease Control is training the model to generate news summaries to support the tracking and prevention of how diseases spread. Speeding Scientific Research in Climate and Beyond In climate research, NCHC supports researchers using the NVIDIA Earth-2 platform to advance atmospheric science. These researchers are tapping Earth-2’s CorrDiff AI model to sharpen the precision of coarse-resolution weather models, and DeepMind’s GraphCast model in NVIDIA PhysicsNeMo for global weather forecasting. They’re also adopting the NVIDIA NIM microservice for FourCastNet, an NVIDIA model that predicts global atmospheric dynamics of weather and climate variables, and using NVIDIA GPUs to accelerate the simulation of numerical weather prediction models. With the new supercomputer, the researchers will be able to run more complex simulations and accelerate the pace of AI training and inference. Advancing Quantum Innovation  NCHC researchers are also advancing quantum research using the NVIDIA CUDA-Q platform and NVIDIA cuQuantum library targeting applications in quantum machine learning, chemistry, finance, cryptography and more. The research institute has developed Quantum Molecular Generator, a tool that generates valid chemical molecules, using quantum circuits and the CUDA-Q platform. It’s also created cuTN-QSVM, an open-source tool built on the cuQuantum library that accelerates large-scale quantum circuit simulations. The tool enables researchers to tackle more complex problems, offering linear scalability and supporting hybrid quantum computing systems to help accelerate the development of large-scale quantum algorithms. NCHC researchers recently used cuTN-QSVM to perform a record-breaking 784-qubit simulation for a quantum machine learning algorithm. The institute also plans to build a hybrid quantum-accelerated computing system by integrating NVIDIA DGX Quantum systems. Learn more about Taiwan’s National Center for High-Performance Computing at NVIDIA GTC Taipei, taking place May 21-22. Watch the COMPUTEX keynote by NVIDIA founder and CEO Jensen Huang.

Credit: Hypershell X Every weekend warrior knows the drill — you sit in front of a computer all week, and when the weekend hits, you bike, hike, and run yourself ragged. Your body feels destroyed on Monday. Repeat.If this sounds like you — or even if you’re a casual exerciser who wants to walk and bike longer distances without getting tired — the future has arrived. The world’s first-ever outdoor exoskeleton, Hypershell X, can help max out your physical abilities with minimal effort.Hypershell X is causing a buzz among both outdoorsy types and robotics enthusiasts, and it won the Best of Innovation in Robotics award at CES 2025.The cyborg-looking device fits like a second skin over your legs and provides up to 800 watts of power, helping you raise your legs and increasing strength up to 40 percent. Whether you’re walking, running, cycling, climbing stairs, or mountaineering, the device’s motor utilizes AI to adapt to your movements in real time, intuitively. Opens in a new window Credit: Hypershell Hypershell X Series From $999 Basically, you feel like yourself, only stronger. Welcome to the future of wearable roboticsThe Hypershell X may look like a sci-fi fantasy device, but you’ll barely feel it while you’re wearing it. Just buckle on the "fanny pack", which also houses the removable and rechargeable battery, and the ergonomic hip levers fit down your legs and are secured by soft straps above your knees. Power the device up via the exoskeleton’s one-touch button, and the M-One motor kicks in, reducing your leg’s physical exertion by up to 30 percent. Mashable Light Speed Want more out-of-this world tech, space and science stories? Sign up for Mashable's weekly Light Speed newsletter. By clicking Sign Me Up, you confirm you are 16+ and agree to our Terms of Use and Privacy Policy. Thanks for signing up! Credit: Hypershell The device itself weighs under five pounds and nicely folds up to fit into your backpack. It can go up to almost 11 miles on one charge, works in temperatures as low as minus-4 degrees Fahrenheit, and the exoskeleton is fully adjustable (think of your over-ear headphones, but with more moving parts) and accommodates different body types.In addition, Hypershell X can offset up to 66 pounds of weight, which is a huge bonus for adventurers who carry packs full of heavy gear.The AI algorithm syncs to your movementsThe Hypershell X uses a combination of AI algorithms, advanced sensors, and robotics to adjust and sync with your movements, so every step feels natural and effortless. The device might even feel different from day to day as it gets to know you, or as you get stronger, which is pretty cool. Credit: Hypershell As for the mobile app, you can use it to fine-tune your movement customizations, track your stats, and watch tutorials — or you can just pack your phone away and enjoy the great outdoors, using the exoskeleton’s button to adjust power levels whenever you want.Like other devices, the Hypershell X also receives firmware updates. One recent update includes multi-user device access, because you know all of your friends are going to want to take it for a spin.Which Hypershell X is right for you?The Hypershell X comes in three different models — the Go X, Pro X, and Carbon X — and each model varies in build material, power, battery range, and price.The least expensive Go X might be a good choice for biking to the park and less demanding activities such as day hikes, as it delivers 400 watts of power at peak output. The Pro X, on the other hand, can deliver twice the power output of the Go X, making it a solid choice for bike commuters, weekend warriors, and moving into your fifth-floor walkup. Last in the Hypershell X lineup, the Carbon X delivers 800 watts of peak power and is the lightest of the three models. It’s a great pick for people who pack in gear such as cameras and camping stoves and want to conquer mountains.Whether you’re facing gnarly hiking trails, long distances, or just biking around town, the new Hypershell X exoskeleton will boost your leg strength so you can go farther with less effort — and less wear on your body.

iSpeedToLead is a fast-growing, innovative marketplace selling motivated seller leads to real estate investors and wholesalers. We’re transforming real estate lead generation through cutting-edge AI-driven solutions, enhancing marketplace liquidity, and optimizing user experiences.Role Mission: Lead the practical deployment and integration of AI technologies across the organization, ensuring all AI initiatives translate into tangible business results and seamless user experiences.Responsibilities:Coordinate the implementation of AI projects across different business functions, including operations, sales, marketing, and customer support.Act as a bridge between AI/ML engineering teams and non-technical stakeholders to facilitate clear communication and effective collaboration.Manage project timelines, ensuring AI initiatives are delivered on schedule and within budget.Troubleshoot and resolve issues during AI project execution, ensuring smooth operational integration.Train internal teams on how to effectively use and leverage AI-driven tools and systems.Design and optimize automation workflows using tools like Make.Develop and refine AI prompts for maximum efficiency and performance in AI-driven features.Requirements:3+ years experience in technical project management or AI implementation roles.Familiarity with machine learning concepts, AI-driven software solutions, and data management practices.Proficiency in project management and collaboration tools such as Jira, Slack, Notion, Monday.com, Trello, and similar platforms.Strong hands-on experience with automation tools (Make.com, Zapier, or similar).Understanding of prompt engineering and optimizing AI model interactions for enhanced outcomes.Excellent organizational and communication skills, able to clearly articulate technical details to non-technical audiences.Strong problem-solving abilities and practical experience in project management methodologies (Agile/Scrum).Prior experience implementing AI solutions in marketplace, SaaS, or real estate tech environments is highly desirable.What Success Looks Like:Timely and successful delivery of AI projects with measurable business impacts.Strong internal adoption and user satisfaction with implemented AI solutions.Effective and efficient communication between technical and business teams.Why Join Us?Work in a dynamic, growth-oriented environment.Directly impact strategic business outcomes through AI innovation.Collaborate closely with a driven, innovative team.Competitive salary, equity opportunities, and career advancement.Next Steps: Excited about driving impactful AI implementations? Apply now and shape the future of AI-driven real estate technology at iSpeedToLead!Apply NowLet's start your dream job Apply now Meet JobCopilot: Your Personal AI Job HunterAutomatically Apply to Remote Product JobsJust set your preferences and Job Copilot will do the rest-finding, filtering, and applying while you focus on what matters. Activate JobCopilot

ASUS is updating both its ProArt laptop and its Chromebooks with the latest internals for Computex 2025, and giving both families of laptops a more premium look, with new colors and tasteful finishes. The ASUS ProArt A16 stands out as the most premium pick, with a black aluminum body, "stealth" hinge that bring the top half of the laptop nearly flush with the bottom and a smudge-resistant finish that should hopefully avoid fingerprints. Inside, ASUS is offering an AMD Ryzen AI 9 HX processor and a NVIDIA GeForce RTX 5070 Laptop GPU, both of which qualify the new ProArt as a Copilot+ PC. That means you'll get access to Windows' growing list of AI features, and ASUS is also including to apps — StoryCube and MuseTree — that can run generative AI models entirely locally. All packed into a laptop that's around half-an-inch thick and has a 16-inch 4K OLED. Asus In terms of Chromebooks, ASUS is offering both normal models and Chromebook Plus versions that support Google's AI tools. The ASUS Chromebook Plus CX34 has a 14-inch display that can fold flat and a 1080p webcam, alongside up to an Intel Core i5 and 8GB of LPDDR5 RAM. That's enough to offer Gemini features locally, and you'll get priority access to Gemini Advanced. The only real disadvantage is the giant ASUS logo that still looks awkward next to the similarly prominent Chromebook logo, and the limited color options: You can only pick between white or grey. Asus The ASUS Chromebook CX14 and CX15 come with up to an Intel Core N355 processor, put to 8GB of LPDDR5 RAM and up to 256GB of storage. If you're curious about Google's AI features, you can also purchase a Plus version of the CX14. Whether you get the 14-inch or 15-inch model, both come with a respectable selection of ports, including HDMI for connecting to external displays. Either size also gets a variety of color options: blue, and a sliver-y grey or a greenish-grey in a either a matte or textured finish. Asus The ASUS Chromebook CX34 is available now starting at $400 from both Walmart and Best Buy. Meanwhile, the rest of the above laptops won't be available until Q2 2025. The ProArt A16 starts at $2,500 from ASUS' online store and Best Buy. The Chromebook CX14 starts at $279 from Best Buy or Costco. The Chromebook Plus CX14 will be available for $429 from Best Buy. And finally the Chromebook CX15 starts at $220 and will be able to be purchased from Best Buy and Amazon.This article originally appeared on Engadget at https://www.engadget.com/computing/laptops/the-asus-proart-a16-laptop-gets-you-the-latest-from-amd-and-a-giant-screen-013037587.html?src=rss

Leading healthcare organizations across the globe are using agentic AI, robotics and digital twins of medical environments to enhance surgical precision, boost workflow efficiency, improve medical diagnoses and more. Physical AI and humanoid robots in hospitals have the potential to automate routine tasks, assist with patient care and address workforce shortages. This is especially crucial in places where challenges to optimal healthcare services are paramount. Such challenges include hospital overcrowding, an aging population, rising healthcare costs and a shortage of medical professionals, all of which are affecting Taiwan, as well as many other regions and countries. At the COMPUTEX trade show in Taipei, NVIDIA today showcased how leading Taiwan medical centers are collaborating with top system builders to integrate smart hospital technologies and other AI-powered healthcare solutions that can help reduce these issues and save millions of lives. Cathay General Hospital, Chang Gung Memorial Hospital (CGMH), National Taiwan University Hospital (NTUH) and Taichung Veterans General Hospital (TCVGH) are among the top centers in the region pioneering healthcare AI innovation. Deployed in collaboration with leading system builders such as Advantech, Onyx, Foxconn and YUAN, these solutions tap into NVIDIA’s agentic AI and robotics technologies, including the NVIDIA Holoscan and IGX platforms, NVIDIA Jetson for embedded computing and NVIDIA Omniverse for simulating virtual worlds with OpenUSD. CGMH Boosts AI-Powered Medical Imaging With an average of 8.2 million outpatient visits and 2.4 million hospitalizations a year,  CGMH estimates that a third of the Taiwanese population has sought treatment at its vast network of hospitals in Taipei and seven other cities. The organization is pioneering smart hospital innovation by enhancing surgical precision and workflow efficiency through advanced, AI-powered colonoscopy workflow solutions, developed in collaboration with Advantech and based on the NVIDIA Holoscan platform, which includes the Holoscan SDK and the Holoscan Sensor Bridge running on NVIDIA IGX. NVIDIA Holoscan is a real-time sensor processing platform for edge AI compute, while NVIDIA IGX offers enterprise-ready, industrial edge AI purpose-built for medical environments. Using these platforms, CGMH is accelerating AI integration in its colonoscopy diagnostics procedures. Deployed in gastrointestinal consultation rooms, the AI-powered tool collects colonoscopy streams to train a customized model built on Holoscan and provides real-time colonic polyps identification and classification. Colonoscopy tools at CGMH. Image courtesy of CGMH. CGMH’s AI infrastructure — comprising NVIDIA accelerated computing, NVIDIA DGX systems, the MONAI framework, NVIDIA TensorRT-LLM open-source library, NVIDIA Dynamo inference framework, and the NVIDIA NeMo and Clara platforms — enables accelerated research and development across the organization. CGMH serves nearly 50 AI agent models that daily help the hospital analyze medical imaging, improving diagnostic accuracy, throughput and real-time inference at scale. For example, NVIDIA Triton-powered AI sped newborn examination record processing by 10x. Cathay General Hospital Improves Diagnostics With AI Cathay General Hospital, a Taipei-based healthcare center that provides hospital management and medical services, has collaborated with National Taiwan University Hospital, medical computer manufacturer Onyx and software provider aetherAI to develop an AI-assisted colonoscopy system that highlights lesions, detects hard-to-spot polyps and issues alerts to help physicians with diagnoses. Polyp detection during colonoscopy. Image courtesy of aetherAI and Onyx. Powered by a compact, plug-and-play AI BOX device — built with the NVIDIA Jetson AGX Xavier module — the AI system is trained on over 400,000 high-quality, physician-annotated images collected from patients with diverse and severe lesions over four years. The system can achieve up to 95.8% accuracy and sensitivity, and studies have shown that it can improve adenoma detection rates by up to 30%. These enhancements assist physicians in reducing diagnostic errors and making more informed treatment decisions, ultimately contributing to improved patient outcomes. NTUH Detects Liver Tumors, Cardiovascular Risks With AI In the 100+ years since its founding, NTUH has nurtured countless professionals in medicine and is renowned for its trusted clinical care. The national teaching hospital is now adopting AI imaging to more quickly, accurately diagnose patients. NTUH’s HeaortaNet model, trained on more than 70,000 axial images from 200 patients, automates CT scan segmentation of the heart, including the aorta and other arteries, in 3D, enabling rapid analysis of risks for cardiovascular disease. The model, which achieves high segmentation accuracy for the pericardium and aorta, significantly reduced data processing time per case from an hour to about 0.4 seconds. In addition, NTUH collaborated with the Good Liver Foundation and system builder YUAN to develop a diagnostic-assistance system for liver cancer detection during ultrasounds. It taps into an NVIDIA Jetson Orin NX module and a deep learning model trained on more than 5,000 annotated ultrasound images to identify malignant and benign liver tumors in real time. YUAN and NTUH’s liver cancer detection system turns an ultrasound device into an AI-assisted diagnostic tool. Image courtesy of YUAN. NVIDIA DeepStream and TensorRT SDKs accelerate the system’s deep learning model, ultimately helping clinicians detect tumors earlier and more reliably. In addition, NTUH is using NVIDIA DGX to train AI models for its system that detects pancreatic cancer from CT scans. TCVGH Streamlines Multimodal Imaging and Clinical Documentation Workflows With AI  Taichung Veterans General Hospital (TCVGH), a medical center and a teaching hospital administered by the Veterans Affairs Council in Taipei, has partnered with Foxconn to build physical and digital robots to augment staffing, improving clinician productivity and patient experiences. Foxconn developed an AI system that can analyze medical images and spot signs of breast cancer earlier than traditional methods, using NVIDIA Hopper GPUs, NVIDIA DGX systems and the MONAI framework. By tapping into clinical data and multimodal AI imaging, the system creates 3D virtual breast models, quickly highlighting areas of concern in scans to help radiologists make faster, more confident decisions. Foxconn is also working with TCVGH to build smart hospital solutions like the AI nursing collaborative robot Nurabot and tapping into NVIDIA Omniverse to create real-time digital twins of hospital environments, including nursing stations, patient wards and corridors. These digital replicas serve as high-fidelity simulations where Jetson-powered service robots can be trained to autonomously deliver medical supplies throughout the hospital, ultimately improving care efficiency. AI nursing collaborative robot Nurabot. Image courtesy of Foxconn. In addition, TCVGH has developed and deployed its Co-Healer system, which integrates the Taiwanese native large language model TAIDE-LX-7B to streamline clinical documentation processes with agentic AI. Co-Healer, built on the NVIDIA Jetson Xavier NX module, processes and helps summarize medical documents — such as nursing progress notes and health education materials — and supports medical exam preparation by providing students with instant access to nursing guidelines and patient-specific protocols for clinical procedures and diagnostic tests. This helps healthcare workers alleviate burnout while giving patients a clearer understanding of their diagnoses. Learn more about the latest AI advancements in healthcare at NVIDIA GTC Taipei, running May 21-22 at COMPUTEX.

The MSI Claw series of Steam Deck-style handheld gaming PCs is the only one from a major manufacturer that goes with Intel chips instead of the much more popular (at least in this segment) AMD APUs. Well, it looks like MSI decided to go with the flow. There’s a new version of the Claw 8, and it’s using an AMD Ryzen Z2 Extreme. That’s the same chip that’s allegedly inside that new Asus ROG Ally 2, a more powerful version than the first generation, and not to be confused with the disappointing Ryzen Z2 Go. This new AMD flavor is christened the Claw A8 BZ2EM, which is only slightly less terrible than the top-end Claw 8 AI+ with Intel chips. The new model is notably more angular, with a two-tone paint job that doesn’t stretch onto the main panel and what looks like larger speaker grilles built into the grips. msi This new AMD-powered Claw comes with an 8-inch, 1200P LCD screen with 120Hz refresh, “up to 24GB” of DDR5x-8000 RAM, one M.2 slot for storage (no capacity given currently), and double USB-C/Thunderbolt 4 ports. You also get a MicroSD card reader for expansion, a beefy 80-watt hour battery, and a weight of 765 grams 1.6 pounds), which is still slightly lighter than the Intel version. Speaking of which, there’s a refreshed model of the Claw 8 AI+ as well. It’s using the same hardware as the existing model, topping out at an Intel Core Ultra 7 258V, 32GB of RAM, and 2TB of storage. This “Polar Tempest Edition” gets a “glittering UV coating,” according to the press release. Strangely, the press release states that both devices will be available in “a range of color options,” but it does not provide specific prices or release dates. The Claw A AI+ has been very difficult to find in the US since launch but is currently listed at $1000 on Best Buy and B&H Photo, with neither actually shipping the hardware. Other announcements from MSI at Computex showcase new OLED monitors, with the MAG 272QP QD-OLED X50 being the most intriguing. If that alphabet soup doesn’t perk up your ears, try this: 500Hz eSports OLED monitor for $850. It has all the other usual gaming bells and whistles, like QHD (2560×1440) resolution at 27 inches, .03ms response time, variable refresh rate support for consoles, and some fancy stuff like support for resizing and custom aspect ratios. It’s using a Samsung panel, probably the same one as this monitor, for quite a bit less. MSI But that price at that refresh rate is really something. As my editor, Brad Chacos, said, you’d expect to pay somewhere in that ballpark for a conventional LCD panel at 500Hz. Upgrading to an OLED, while also offering fantastic speeds for gaming, is really something. Connection options aren’t fully spelled out in the PR material, but it has a USB-C port, hopefully with enough wattage output for a gaming laptop. The MPG 271QR QD-OLED X50 (oh my god MSI, you are just begging for returns here) has that same 500Hz 27-inch panel, but builds in some more advanced features. The headliner is the new AI Care Sensor and its accompanying panel protection features. It only needs a mandatory OLED care refresh cycle once every 24 hours instead of 16, thanks to a local “AI” chip presence detection and automatic dimming. Surprisingly, all these extra features only raise the price a little, up to $899 USD. The cheaper MAG monitor is scheduled to go on sale starting July 5th, and the more advanced MPG on July 17th. Precise location availability was not shared.

Hardware announcements are already coming in hot and fast at Computex, but one bit of news from Gigabyte marks a significant change for the company, which is best known for its desktop components and gaming laptops: Gigabyte desktops are on the way. The decision to move into the consumer desktop space might seem odd, given the decline of desktop computing in recent years, but Gigabyte is banking on one major factor: AI.New Pre-Built Desktop PCs for AIOne of Gigabyte's most interesting Computex announcements is its first line of consumer desktop PCs built for gaming and AI. The first is the AI TOP 100 Z890, an ultrapowerful AI-focused desktop that features a liquid-cooled Intel Core Ultra 9 285K processor, an Nvidia GeForce RTX 5090 GPU, and 128GB of DDR5 memory. The AI TOP 100 Z890 targets small businesses, startups, academics, and AI enthusiasts. This product comprises many of Gigabyte's own AI TOP components, like the Z890 motherboard, AI-ready SSD storage, and a 1600-watt (W) PSU. Together with the silicon parts, these combine to create a powerful machine for AI productivity and 4K gaming.The second is the AI TOP 500 TRX50, but details on this model are thin. I suspect this model contains the same TRX50 AI TOP motherboard we saw at Computex last year. Equipped with four PCIe x16 slots, four NVMe M.2 slots, dual 40Gbps USB Type-C ports, a pair of 10GbE wired LAN controllers, a Wi-Fi 7 radio, and a 16+8+4 power phase design, it's one of the best new motherboards we've seen and should make for an incredible pre-built desktop.(Credit: John Burek)Gigabyte has made a concerted effort to capitalize on the AI gold rush of the last two or three years, aggressively making and selling AI data center hardware. Specifically, these are "AI TOP"-branded components and motherboards designed for the unique demands of AI workloads.Purpose-built motherboards with high-end hardware, robust power delivery, and advanced connectivity are already in Gigabyte's stable. These provide AI must-haves like multi-GPU scalability, high-capacity and high-speed memory support, and specialized thermal management to monitor temperatures during heavy AI workloads.Components have also enjoyed Gigabyte's AI upgrades. Gigabyte has AI-specific models of top graphics cards, high-endurance SSDs, and even power supplies that support AI tasks better than the average PSU. The specifics vary from part to part, but these individual components generally work on the same principle of combining server-grade components with modern desktop PCs' flexibility and upgradability. Gigabyte even offers bundle deals, letting shoppers buy a whole system's worth of equipment for easy assembly.Now, those offerings combine into a pair of premium gaming and AI-empowered desktop computers. Instead of bundled components for DIY builders, these are pre-built systems, ready to go right out of the box.Gigabyte Is Going After Desktop Gamers TooBut it's not all about AI hardware for Gigabyte. The company is also making a play for a more traditional desktop buyer with a handful of new gaming desktops and desktop kits.Recommended by Our EditorsThe first is the Aorus Supreme 5 / ICE, which combines a premium Gigabyte X870E motherboard with your choice of GeForce RTX 5090 and 5080 graphics cards. Meanwhile, the Aorus PRIME 5 uses a Gigabyte B850 motherboard and AMD Ryzen 7 9700X processor with GeForce RTX 5080 and 5070 Ti GPU options.(Credit: Gigabyte)Finally, for the pickiest PC builders, Gigabyte's new Stealth PC build kit presents an ultra-clean design that hides cables and connectors and packs top components into a gorgeous chassis.Gigabyte says that the kit will come with your choice of the X870 Aorus Stealth Ice or B850 Aorus Stealth Ice motherboards, and an Aorus GeForce RTX 5090 STEALTH ICE 32G graphics card, along with plenty of other Gigabyte components to select from. And while you can put this build in any case you like, it will also be offered with the Gigabyte C500 Panoramic Stealth Ice chassis, which features tempered-glass front and side panels that give the case a 270° panoramic view of the internals.Gigabyte has yet to provide any information about pricing or availability, but judging by the price of the individual components, we already know these won't be cheap.At Last, a Pair of New Gigabyte Gaming LaptopsDesktops may be the big focus for Gigabyte at Computex, but Gigabyte also has a couple of new gaming laptops. Instead of the Aorus or Aero brands, these are part of the company's mainline gaming brand, with the Gigabyte Gaming A18 and the Gigabyte Gaming A16 Pro.The Gigabyte Gaming A16 Pro is a slim gaming machine, less than 20mm thick. It houses an Intel Core 7 240H processor and Nvidia GeForce RTX 5080 mobile GPU, all supporting 115W max TGP. With up to 32 GB dual-channel LPDDR5x memory and dual SSD slots for 4TB of total storage, you'll find a lot of capability packed into this slim laptop chassis.Dominated by an 18-inch display, the larger Gigabyte Gaming A18 drips with gaming goodness. The giant IPS-level panel has ultra-slim bezels on all four sides, a 165Hz refresh rate, up to WUXGA resolution, and a blistering 3 millisecond (ms) response time.This laptop, equipped with your choice of Intel Core 7 240H or AMD Ryzen 7 260 processors and an Nvidia GeForce RTX 5070 graphics card, should pump out seriously speedy gaming performance.As of this writing, Gigabyte has not announced pricing or availability for any of the systems discussed above. We will update this story with further announcement details from Computex and additional coverage as these products arrive later in the year.

Few things ruin a nice night spent outside quite like mosquitoes. There are some great DIY methods for keeping these beasties away from your blood (including a mosquito kill bucket), but I prefer to use a Thermacell. Right now, Amazon has these rechargeable electronic repellent devices on sale for their lowest prices of the year so far. At the time of writing, Prime members can still get delivery well before the upcoming Memorial Day weekend. Thermacell E-Series Rechargeable Mosquito Repeller with 20’ Mosquito Protection Zone — $32 (was $40) This little device creates a 20-foot bug-free zone around you and your guests. Thermacell Candles do an OK job chasing away mosquitoes, but science can do better. Thermacell developed its proprietary repellent material that went through independent testing and EPA approval. Plug a cartridge into the device, and it diffuses that repellent into a 20-foot bug-free zone. It works silently and with only a very slight smell that’s a far cry from the overwhelming scent of a mosquito candle. The model currently on sale is the best option for most people. It has the company’s most recent diffusion technology, and the battery lasts up to 6.5 hours on a single charge. A rapid charging function allows you to get several hours of operation with less than half an hour of charging, so you won’t be totally out of luck if you forget to charge it before guests arrive. Thermacell Rechargeable Mosquito Repeller Refills; Advanced Repellent Formula — $46 (was $55) You’ll never be bummed to have extra refills on-hand. Thermacell You’re going to need some refills if you buy one of these devices, and they’re on sale right now. This kit provides a total of 120 hours of operation in three easy-to-swap cartridges. It’s always good to have more refills on hand so you’re not stuck without them. More Thermacell mosquito repellent device deals Thermacell repellent refill deals Thermacell E-Series Rechargeable Mosquito Repeller with 20’ Mosquito Protection Zone $43 (was $50) Thermacell Rechargeable Mosquito Repeller Refills $18.69 (was $22) Thermacell Rechargeable Mosquito Repeller Refills 240 hours $73 (was $100)