UnitedHealth has confirmed the ransomware attack on its Change Healthcare unit last February affected around 190 million people in America nearly double previous estimates.The U.S. health insurance giant confirmed the latest number to TechCrunch on Friday after the markets closed.Change Healthcare has determined the estimated total number of individuals impacted by the Change Healthcare cyberattack is approximately 190 million, said Tyler Mason, a spokesperson for UnitedHealth Group in an email to TechCrunch. The vast majority of those people have already been provided individual or substitute notice. The final number will be confirmed and filed with the Office for Civil Rights at a later date.UnitedHealths spokesperson said the company was not aware of any misuse of individuals information as a result of this incident and has not seen electronic medical record databases appear in the data during the analysis.The February 2024 cyberattack is the largest breach of medical data in U.S. history and caused months of outages across the U.S. healthcare system. Change Healthcare, a health tech giant and UnitedHealth subsidiary, is one of the largest handlers of health, medical data, and patient records; its also one of the biggest processors of healthcare claims in the United States.The data breach resulted in the theft of massive quantities of health and insurance-related information, some of which was published online by the hackers who claimed responsibility for the breach. Change Healthcare subsequently paid at least two ransoms to prevent further publication of the stolen files.UnitedHealth previously put the number of affected individuals at around 100 million people when the company filed its preliminary analysis with the Office for Civil Rights, the unit under the U.S. Department of Health and Human Services that investigates data breaches.In its data breach notice, Change Healthcare said that the cybercriminals stole names and addresses, dates of birth, phone numbers, email addresses, and government identity documents, which included Social Security numbers, drivers license numbers, and passport numbers. The stolen health data also includes diagnoses, medications, test results, imaging, and care and treatment plans, as well as health insurance information. Change said the data also includes financial and banking information found in patient claims.The breach was attributed to the ALPHV ransomware gang, a prolific Russian language cybercrime group. According to testimony by UnitedHealth Groups CEO Andrew Witty to lawmakers last year, the hackers broke into Changes systems using a stolen account credential, which was not protected with multi-factor authentication.How the ransomware attack at Change Healthcare went down: A timeline

One of the larger mercantile buildings in the Leather District of Boston is this turn-of-the-century block,historically known as the South Street Building. Bounded by three streets, this eight-story building was constructed in 1899from plansbyWinslow, Wetherill & Bigelowand is a great example of a Classical Revival style commercial block with Beaux Arts motifs to further decorate the facades. In 1901, as expected, the city directories list many leather and soft goods-related occupants in the building, including: The American Calfskin Leather Company, John F. Moore Co., leather dealer, and Charles D. French, leather remnants dealer. The building was renovated in 1990 and rebranded as Lincoln Plaza, becoming a major space for non-profit offices.

Kayla Solino/ZDNETZDNET's key takeawaysThe Strapsicle silicone straps upgrade the grip options on your Kindle and provide a secure hold to prevent drops.At $21, Strapsicle is an easy and affordable Kindle accessory to make your reading experience even more comfortable.If you prefer more ergonomic grips or don't like the look of straps across the back of your Kindle, an alternative security option may be best.If you're an avid e-reader like me (or even if you're new to the Kindle world), you probably quickly figured out how uncomfortable it can be to use the e-reader. That's not because my Kindle Paperwhite is bad, but because it's sometimes hard to find the perfect position for optimal reading enjoyment.Kindles do not have built-in support, making reading in bed, at the pool, at the beach, or anywhere a lot more challenging, especially if you like to read lying down or at odd angles.And just like it's popular to outfit our smartphones with grips, rings, and other accessories for stability, it's quite en vogue to do the same for our other tech, including Kindles. After one too many times dropping my Kindle Paperwhite onto my face (that thing does, in fact, leave a mark), I finally caved and was seriously in the market for a grip system.During my journey, I encountered some of the usual accessory contenders: traditional grips like PopSockets, cases that convert to stands, and large, clunky holders. But something else caught my eye --Strapsicle. details View at Amazon I stumbled upon them online. Strapsicle is a stability option created for e-readers like the Kindle and Kobo to ensure a comfortable grip when you read, and a secure hold for your Kindle when you're not (you know, like when you fall asleep with the device in your hand). Strapsicles are simple silicone pieces that pop over the corners of your device and create a strap to handle your Kindle securely.So, where had this accessory been all my life? The answer is that Strapsicle has a large cult following of users, many derived from BookTok, but the accessory hasn't quite made it mainstream. But that situation may be about to change. Just this month, the Australian-based brand sealed a $250,000 deal on Shark Tank Australia. And as a new adopter of Strapsicle, here's why I'm a fan for the foreseeable future.The Strapsicle fits most e-readers, creates a secure grip, and adds a layer of protection, too. The accessory comes in several fun colors, including blush pink (pictured in this article), lilac, sage green, and more. The staps come in four sizes: Small, Medium, Large, and Kindle Oasis, and a handy size chart makes it easy to match the Strapsicle with your respective e-reader model. Holding my Kindle Paperwhite upside down using both Strapsicles as support. Kayla Solino/ZDNETSince I have the Kindle Paperwhite 6.8-inch 11th Gen 2024 model, I purchased the large size. In the box, I received two silicone straps labeled "top left" and "top right", which made it easy to set up my Kindle (seriously, it took less than 60 seconds to set them up).You can use both straps simultaneously or choose to only use one strap on your device, depending on your preference. I tested both approaches, and I prefer having both straps on, especially since the silicone corners add some protection, too.Having a Strapsicle allows me to place my hand wherever I want on my Kindle without worrying about security. This feature is why I chose to try this strap model instead of more conventional methods, like a PopSocket, which can only be fastened in one spot. I can flip my Kindle upside down and all around, and it doesn't budge.PopSocket vs. StrapsicleBefore I start, let me say that I am not anti-PopSocket. I enjoyed using a PopSocket on my iPhone throughout my teens, but once I began working at ZDNET, it became increasingly impractical to continue using one on my phone.I spent a lot of time testingMagSafe accessories, and it became annoying to change cases every time I tested products. I also didn't love using a PopSocket enough to purchase a newer MagSafe version. All that said, a PopSocket was still my first thought when considering a grip for my Kindle.According to Reddit, PopSockets are widely used by avid readers on their devices. They're an affordable and personable option for adding a grip to your Kindle. I do see the appeal. Kayla Solino/ZDNETMy biggest concern with adding a PopSocket to my Kindle was its placement. Should I put it in the center? Off to one side? It turns out that some Redditors had thesame issues.While some said they preferred a PopSocket for its more ergonomic grip, others agreed that it was pretty annoying to only be able to grip your Kindle from one spot. One Redditor even admitted using two PopSockets on her Kindle to combat this issue.The placement concerns, and other adherence issues (would it stick to my case?), ultimately pushed me away from the PopSocket option and towards trying Strapsicle. Plus, while basic PopSockets are under $12 on Amazon, some more intricate and fun designs cost up to $35, which I think is quite expensive.Other Redditors said that they liked the Strapsicle for its added security, thanks to its silicone corners, customizable placement (which allows you to grip from anywhere on your Kindle), and the fact that it didn't pinch their pinky like PopSockets do for some people.I agree with these individuals. I experience no pinching or cramping in my hands using Strapsicle, even for long reading stints, and I love that I can read securely from anywhere and at any angle without worry. Plus, the Strapsicle is easy to clean and wipe down, and I can remove the accessory without hassle. The Strapsicle, in short, is phenomenal, and I can't believe it cost me just a smidge more than $20 because I would've paid way more for something that brings this kind of functionality. Only one Strapsicle placed on my Kindle Paperwhite. Kayla Solino/ZDNETIf I'm being picky (which I am; it's my job), the criss-cross Strapsicle look may not be for everyone. I don't care too much about the back of my Kindle. But if you are into aesthetically pleasing tech, you may want to consider the PopSocket route.The straps could also fit around my case a little better. I have a simple, flexible, clear case on my Kindle Paperwhite, and while the straps fit fine around the corners, they do have a sort of puckering that prevents them from laying flush. However, I don't mind because the straps add padding to my Kindle's corners and work so well.Just keep in mind that there's a chance that the Strapsicle may not fit with your existing case, so you'd need to buy a new one or go without. Strapsicle does sell its own clear case to accompany the straps.ZDNET's buying adviceMy bottom line here: Strapsicle has created lightning in a bottle in a near-monopolized Kindle accessory market. These simple silicone straps are functional, easy to use, and affordable. At $21, a pair of Strapsicles feels like a much better buy than a singular PopSocket, but to each their own.I do not doubt that Strapsicle will probably be on store shelves in the future and become synonymous with the e-reader experience. I have nothing bad to say about this accessory because my face is now protected from my Kindle, which was exactly the problem I needed to solve. Props to Strapsicle, and I hope I can get these straps for my iPad someday.Featured reviews

Anker's MagGo 3-1 wireless charger is an ultraportable device that's dethroned even my favorite travel charger -- and it's 24% off.

Large-scale datasets of millions or billions of ready-to-go AI personas are now available.gettyIn todays column, I showcase a novel twist on the prompting of personas when using generative AI and large language models (LLMs). The trick is this. You conventionally enter a prompt describing the persona you want AI to pretend to be (its all just a computational simulation, not somehow sentience). Well, good news, you no longer need to concoct a persona depiction out of thin air. Instead, you can easily dip into massive-sized datasets with ready-made persona descriptions and then paste those depictions directly into your persona-stirring prompts. Easy-peasy.Lets talk about it.This analysis of an innovative AI breakthrough is part of my ongoing Forbes column coverage on the latest in AI including identifying and explaining various impactful AI complexities (see the link here).Prompt Engineering And PersonasReaders might recall that I previously posted an in-depth elicitation of over fifty prompt engineering techniques and methods, see the link here. Among those myriad approaches was the use of personas, including individual personas and multiple personas, as depicted at the link here, and the much larger scale mega-personas at the link here. Personas are a powerful feature available in LLMs, yet few users seem to be familiar with the circumstances under which they should consider invoking the capability.A persona consists of telling generative AI to pretend to be someone and simulate what that person might know or say. No special setup or elaborate instructions are needed to get this undertaken. I will be providing you in a moment with prompts that show how this is readily performed.A quick example of the value of personas might be helpful here.One of the most popularly invoked personas entails generative AI pretending to be Abraham Lincoln. A teacher might tell a generative AI app such as ChatGPT to simulate the nature of Honest Abe. Students then access the pretense or persona. In an amazing flair, the AI seemingly responds as we assume Lincoln might have responded.Of course, this is based simply on the numerous speeches, written materials, and other collected writings that suggest what he was like. The AI has pattern-matched computationally on those works and mimics what Lincolns tone and remarks might be. Anyone using a generative AI persona needs to keep their wits about them and realize that the conversation or engagement is nothing more than a mimicry or imitation. Though the AI appears to often convincingly fake the nature of the person, it is all still a computational simulation.AI Personas Of Unnamed CompositionsYou dont need to only use names of well-known celebrities or historical figures when seeking to instigate an AI persona.Another equally fine approach consists of describing the overall nature of a persona that you want to have invoked. For example, I might enter a prompt stating that I want a persona consisting of a teenager who is a football player at their high school and has been lately having second thoughts about whether to pursue a sports career right away or continue into college.Why would I craft such an AI persona?Maybe Im training to be a career counselor and want to practice honing my counseling techniques by using generative AI. I could readily come up with lots of scenarios that involve complex situations facing teens. The AI would go back and forth with me as I try to give career advice. It is handy since I can practice as much as I like and not worry about miscuing an actual teenager. Furthermore, the vast number of scenarios that I can conjure up would almost certainly be more than the actual count of teens that I will be potentially advising.Devising From Scratch Or From DatasetThe most common way to indicate an unnamed AI persona is simply to describe the characteristics of the pretense involved. You usually do this out of your own head, in the sense that you think about what factors are crucial and then compose those into your desired prompt. It takes a bit of thinking but can be readily undertaken.Things become slightly more complicated when you want to do a slew of AI personas. Now, you are forced to come up with a myriad of AI personas that fit what you want to do. You might also find yourself staring blankly at an empty prompt and trying to decide what is the best way to word the AI persona that you want to instantiate.No worries.AI researchers have realized that users and other AI analysts might find immensely useful a dataset of AI persona descriptions. The beauty is this. All you need to do is search the dataset to find what you are interested in as an AI persona. Voila, you then copy the description and paste the depiction into a prompt in generative AI.You can do this repeatedly.It goes like this. You find another AI persona description and use that one. You can even grab a bunch of them all at once and feed them as a group into a prompt. Rinse and repeat. Proceed as befits your needs.An added advanced approach would be to use an online tool to dig into the dataset, pull out the AI persona descriptions, and feed them directly into generative AI. This could be a third-party tool, or you can have generative AI potentially do so for you if the AI app has suitable capabilities to allow this functionality.Examples Via Some Existing DatasetsThere are various AI persona datasets available online.I am going to look at one called FinePersonas and another dataset known as PersonaHub. The datasets that provide AI personas are pretty much all relatively similar. The typical format is a spreadsheet-like structure that houses the AI persona descriptions. You can search by hand or use a tool if they provide one. Conventional spreadsheet skills are usually all that you need to know.I went into FinePersonas which is on HuggingFace and opted to semi-randomly pull an AI persona description that caught my interest:A high school physics teacher who enjoys applying physics concepts to various sports, curious about the effects of water resistance and body positioning in swimming.I then used that text in a prompt and got AI to pretend to be that persona.Here we go.My entered prompt: You are to undertake a persona that is based on this description: A high school physics teacher who enjoys applying physics concepts to various sports, curious about the effects of water resistance and body positioning in swimming. I want you to have this persona think aloud and explain what they are mulling over while watching a swim meet.Generative AI response: "Alright, so watching these swimmers, I cant help but think about the physics at play. Look at their body positioning streamlining is key to reducing drag. The more they minimize surface area against the water, the less resistance they face. And their strokeseach pull has to maximize propulsion while keeping turbulence low. I wonder how much energy is being lost to eddies forming behind their hands. Fascinating stuff!"You can see that the AI pretended to simulate the aspects of that chosen AI persona.Nice.Playing Around With AI PersonasYou dont have to be dogmatic about using the AI personas strictly as specified in the datasets.After seeing the response by AI to the above persona of a physics teacher, I decided to change or adjust the persona to explore an alternative aspect.This is what I did.My entered prompt: Adjust the persona so that the physics teacher is an art teacher. What might be going through their mind while watching a swim meet?Generative AI response: "Watching these swimmers, Im struck by the rhythm and flow of their movements it's almost like a living brushstroke on a canvas of water. The way their bodies cut through the pool creates ripples that shimmer under the lights, almost like abstract patterns. And those diving starts? Such a perfect arc of motion, like a sculpture in flight, frozen for just a moment.Multiple AI Personas At Your FingertipsIn those two examples, I used first a physics teacher and then an art teacher. I might want to run through a wider range of teachers that cover a variety of academic specialties.You can invoke multiple AI personas and use just the one from the dataset as the core baseline.Take a look.My entered prompt: Based on the persona that Ive given you, vary the personas for fifteen different types of teachers in terms of the academic disciplines they are in. For each of the fifteen new personas that youve created, once again show me what each is thinking when watching a swim meet.Generative AI response: Here are the fifteen personas that I devised based on the persona you provided, and their respective thinking-aloud mindset while watching a swim meetI recently covered the use of multiple AI personas that represent expert-level specialists in just about any domain you might be examining, see the link here if thats something you are interested in doing.Things To Know About AI Persona DatasetsDuring my classes on prompt engineering, I walk through the use of AI personas and when we get to the matter of persona datasets, I mention that these are some notable ways to make use of pre-cooked or canned personas:(1) Persona as is. Select a particular persona and use it in generative AI.(2) Persona adjusted. Select a particular persona, adjust it to your suitability, and use it in generative AI.(3) Persona as baseline. Select a persona as a baseline, have the AI replicate it in variations, and use it in generative AI.(4) Set of personas. Select a set of personas, specify how they are to be used, and proceed to use them in generative AI.Etc.I also urge the attendees to consider these ten vital elements when deciding which AI persona dataset will best fit their needs:(1) Size of the personas dataset.(2) Stipulation of what each persona consists of.(3) Level of granularity associated with the personas.(4) Various mixes and types which are available.(5) Applicability to your interests.(6) Potential biases embedded in the personas.(7) Ease of utilizing the personas.(8) Any costs associated with the usage of the dataset.(9) Potential copyright considerations if any.(10) Availability of the personas dataset.The surprise for many is that the number of AI personas in these datasets is usually in millions or billions of instances.Say what?Yes, it isnt just a few hundred instances or several thousand, these datasets often are rather vast.This isnt overly shocking when you realize that most of these datasets are crafted by using AI or some related online tool. The person devising the dataset tells the AI or tool to generate tons and tons of personas and store them in a dataset.That being said, I dont want to seemingly diminish the heroic and thankful effort of those who put together these datasets. There is admittedly more elbow grease and hard work that goes into establishing a useful and usable personas dataset. No magic wand makes it appear magically.Some Background On Specific DatasetsI mentioned that I had plucked the physics teacher AI persona out of the FinePersonas dataset that is on HuggingFace. The posted site indicates that its dataset has these core properties (excerpts):Open dataset of 21 million detailed personas for diverse and controllable synthetic text generation.FinePersonas contains detailed personas for creating customized, realistic synthetic data.With this dataset, AI researchers and engineers can easily integrate unique persona traits into text generation systems, enhancing the richness, diversity, and specificity of synthetic outputs without the complexity of crafting detailed attributes from scratch.Shifting gears, consider another persona dataset, called PersonaHub.The PersonaHub dataset touts that it contains a billion personas and has an accompanying research paper describing the collection the paper is entitled Scaling Synthetic Data Creation with 1,000,000,000 Personas by Tao Ge, Xin Chan, Xiaoyang Wang, Dian Yu, Haitao Mi, and Dong Yu, arXiv, September 24, 2024. Here are some salient excerpts explaining the creation and use of the dataset:We propose a novel persona-driven data synthesis methodology that leverages various perspectives within a large language model (LLM) to create diverse synthetic data.To fully exploit this methodology at scale, we introduce Persona Hub a collection of 1 billion diverse personas automatically curated from web data.These 1 billion personas (13% of the worlds total population), acting as distributed carriers of world knowledge, can tap into almost every perspective encapsulated within the LLM, thereby facilitating the creation of diverse synthetic data at scale for various scenarios.By showcasing Persona Hubs use cases in synthesizing high-quality mathematical and logical reasoning problems, instructions (i.e., user prompts), knowledge-rich texts, game NPCs and tools (functions) at scale, we demonstrate persona-driven data synthesis is versatile, scalable, flexible, and easy to use, potentially driving a paradigm shift in synthetic data creation and applications in practice, which may have a profound impact on LLM research and development.As the first version of Persona Hub, although it already contains 1 billion personas, the descriptions of these personas are focused only on major aspects and lack fine-grained details (e.g., preferences for colors and numbers; specific family backgrounds, historical contexts, and life experiences). We plan to refine the personas in subsequent versions of Persona Hub, aiming for their descriptions to be as detailed as those found in Wikipedia articles about individuals.As you might observe, the AI personas in these datasets can be a one-sentence affair or can be lengthier text depictions. The sky is the limit in the sense that these depictions could be devised as extraordinarily detailed. An entire extensive faked background could be contrived and placed into the dataset for use.Use AI Persona Datasets When NeededI would venture that the average use of AI personas in generative AI is usually based on something a particular person has in their mind as to what the persona is supposed to be. They probably wouldnt see much need in using an AI persona dataset. They have a one-and-done mindset.Good for them.For others, if you are conducting a subject-based study and want to have a swath of AI personas, or if you are unsure of what AI persona you want to invoke, these datasets can be quite valuable. Indeed, any kind of large-scale testing of AI or using AI to generate lots of outputs of synthetic data can be streamlined by leveraging an AI persona dataset.No need to derive AI personas from scratch when you can leisurely and conveniently lean into an AI persona dataset.John Rockefeller famously said this: The key to success is not just hard work, but smart work. Keep in the back of your mind that there are AI persona datasets sitting out there and waiting for you to use them. This could reduce the hard work you are doing and aid you in working smarter.Thats a worthwhile human persona to aspire toward.

StrandsNew York TimesLooking for Fridays Strands hints, spangram and answers? You can find them here:I am not exaggerating when I say that this has one of the wildest words I have ever seen in a puzzle here, and I would be shocked if even 1% of players got it. Which maybe why you are here.How To Play StrandsThe New York Times Strands puzzle is a play on the classic word search. Its in beta for now, which means itll only stick around if enough people play it every day.Theres a new game of Strands to play every day. The game will present you with a six by eight grid of letters. The aim is to find a group of words that have something in common, and youll get a clue as to what that theme is. When you find a theme word, it will remain highlighted in blue.Youll also need to find a special word called a spangram. This tells you what the words have in common. The spangram links two opposite sides of the board. While the theme words will not be a proper name, the spangram can be a proper name. When you find the spangram, it will remain highlighted in yellow.Be warned: Youll need to be on your toes.Some themes are fill-in-the-blank phrases. They may also be steps in a process, items that all belong to the same category, synonyms or homophones, The New York Times notes. Just as she varies the difficulty of Wordle puzzles within a week, [Wordle and Strands editor Tracy] Bennett plans to throw Strands solvers curveballs every once in a while.MORE FOR YOUWhat Is Todays Strands Hint?We will start with the official NYT hint and then move on to one of my own, as I think youll need the help this week especially. The official hint is:Seeing double Mine is:Two in a rowHard to think of a second one this time, admittedly.What Are Todays Strands Answers?We will begin with the spangram in the answer portion here, where spoilers follow. Then I will post all the answers below that. Here is the spangram:LETTERSAnd where you find it:StrandsNYTAnd the answers:COMMITTEECOFFEEBALLOONSUCCEEDWHIPPOORWILLStrandsNYTWhat the hell is a WHIPPOORWILL? Even spell check has no idea here. I thought this was Whirlpool but you cant make that work, and you need double double letters for this puzzle here. So, after looking it up, of course, a Whippoorwill is a bird. A bird I have never heard of in my life despite living in North America where it resides. Native Americans said that hearing its cry was a death omen, and I certainly wanted to die after trying this many combinations of letters. Wow.Follow me on Twitter, YouTube, and Instagram.Pick up my sci-fi novels the Herokiller series and The Earthborn Trilogy.

Table of ContentsTable of ContentsWhos playing in Super Bowl LIX?What time is the Super Bowl?Is Super Bowl LIX in 4K and HDR?How to stream Super Bowl 2025 if you dont have cableSuper Bowl LIX is fast approaching, with only the Conference Championship games and a couple weeks until we find out who will top the NFL in 2025. This year, the big game will be at the home of the New Orleans Saints the Caesars Superdome and is the 11th time New Orleans hosts the Super Bowl (and eighth time at the Superdome).As youd expect for one of the biggest sporting events on the planet, there are going to be plenty of ways to watch the game, including cable, satellite, streaming, and OTA options. Lets get into the details.Recommended VideosAs of this moment, we dont have an answer just yet, as both the AFC and NFC Championship games take place this Sunday, January 26. The action starts at noon ET as the Philadelphia Eagles welcome the Washington Commanders to the Linc Lincoln Financial Field. A few hours later, at 3:30 ET, defending Super Bowl champs, the Kansas City Chiefs, face off against the Buffalo Bills at Arrowhead Stadium.RelatedThe winner of each game will meet on the field of Caesars Superdome on Sunday, February 9 to determine the 2025 Super Bowl champion.Super Bowl LIX is set to kick off at 6:30 p.m. ET from Caesars Superdome in New Orleans (which is 5:30 p.m. local time). Pregame coverage, though, will start a few hours earlier on Fox at 3 p.m. and post-game coverage should start around 10 that night (unless we see the third Super Bowl overtime game in history).You can also stream it from the Fox Sports app or Fubo, if you happen to subscribe to the service. In addition, for the first time, the entirety of the days coverage will be available on the free streaming service Tubi, including an exclusive pre-game red carpet event hosted by Olivia Culpo at 3:30 p.m. ET. And if you do stream the entire coverage through Tubi, fear not, youll be able to see all of those Super Bowl commercials, too.Yes, Super Bowl LIX will be available in 4K resolution on Fox and on Tubi. This also includes the halftime show with Grammy Award-winning artist, Kendrick Lamar. The broadcast will also be available in HDR on supported 4K HDR devices.Phil Nickinson / Digital TrendsIf you dont have access to Fox via a cable subscription or satellite service, you could get yourself an OTA antenna and connect it to your TV, or use a box like Tablo to make that over-the-air signal available to multiple devices in your home. Place the antenna as high as you can in your room, or better yet, outside on the roof. For those that have cut the cord, we recommend having an antenna in your setup. Be aware, though, that the ability to get channels will depend on your topography and nearby buildings. Once youve made the initial antenna purchase, though, its all free content.Theres also the aforementioned Tubi option for free streaming (you just need to sign up for an account). Those with YouTube TV will again have the ability to watch on the popular live streaming service. As with Fox and Tubi, YouTube TV should have the broadcast in 4K, although YouTube TVs 4K service is an add-on. (You can also sign up for a free preview and watch the game if you dont have a current subscription.)Phil Nickinson / Digital TrendsAs weve already said, Fubo will carry the game, and it has one thing YouTube TV doesnt 4K content without an additional fee.No matter what, there are plenty of ways to catch the big game. Just make sure to grab yourself a big-screen TV before the game as well. TCL has some incredible deals, including a $1,500 98-inch Q6.Editors Recommendations

html PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN" "http://www.w3.org/TR/REC-html40/loose.dtd" Table of ContentsTable of ContentsWhy so long?Fantastic hardwareIts a hard act to followThe Samsung Galaxy S25 Ultra is going to be my primary smartphone for at least the next few weeks, and Im coming to it from the OnePlus 13. I first put my SIM card in the OnePlus 13 three months ago, and no one has been able to wrestle it from my hands since. For me, this is an astonishingly long time to use an Android phone, and it speaks volumes about what a superb phone it is.Ill be using the Galaxy S25 Ultra for the next few weeks, but Im going to miss the OnePlus 13. Heres why.Recommended VideosAndy Boxall / Digital TrendsTwelve weeks of use may not sound like much to you, but its probably the longest continuous period of time Ive used a single Android phone for in quite some time. My job involves me swapping Android phones very regularly, but various things aligned to mean I didnt need to swap over the festive period. Often, when these situations have arisen in the past, Ive put my SIM into another phone just to revisit it, or because I really liked it.RelatedIt didnt even cross my mind this time. I even remember saying, during a planning session for future articles, that I wasnt done with the OnePlus 13, even though my review and other coverage was complete. For me to want to continue using the OnePlus 13, even though various other phones Ive really liked were waiting for me, meant it wasnt doing anything badly at all, and perhaps best of all, it wasnt doing anything to annoy me.Ive had a love/hate affair with OxygenOS since much of what I didnt like about Oppos ColorOS began to creep into the design and interface. These aspects the seemingly endless system notifications, poor notification support, and overly complex menus, for example would have seen me reaching for the Google Pixel 9 Pro Fold (my other favorite Android phone of last year) in days gone past, but with OxygenOS 15, OnePlus has taken back control and the software is all the better for it. Im not simply tolerating it. I like it.Andy Boxall / Digital TrendsIve had the OnePlus 13 inside the official Sandstone case since it arrived. Apart from the odd requirement to put a sliver of plastic inside to ensure you get the fastest wireless charging speeds, its a very pleasant addition to the phone. The grippy texture isnt too grippy, so it goes in and out of my pocket without a fight, and it doesnt add too much bulk to the phone.When I take the case off, I do feel silly for using it all the time though. The soft, tactile texture of the microfiber vegan leather back panel on my Midnight Ocean model is far more luxurious than the scratchy, sandpaper-like case. The phones design is spot-on, and a considerable improvement over the OnePlus 12. Small changes like moving Hasselblads H logo to the side of the camera module, and adding a polished line beneath it, make it eye-catching and distinctive.1 of 53x Portrait mode Andy Boxall / Digital Trends Wide-angle Andy Boxall / Digital Trends Andy Boxall / Digital Trends 3x zoom Andy Boxall / Digital Trends Andy Boxall / Digital Trends The battery life continued to impress, and with my two-to-three hours of use each day it lasted well into a third day before I really needed to recharge it. The Qualcomm Snapdragon 8 Elite hasnt made the phone too hot, and Ive loved using the camera too. Hasselblads work behind the scenes must be paying off, as the tone and colors produced in photos are really attractive, and give the OnePlus 13s camera an identity of its own. Ive even discovered a love for the XPan camera mode, which has improved enough for me to no longer consider it a gimmick.Andy Boxall / Digital TrendsThe Galaxy S25 Ultra has to follow what I think is one of the very best Android smartphones you can buy. For it to win me over, and encourage me to at the very least want to use it for 12 consecutive weeks, it has to be easy to carry around, look good, have excellent battery life, reliable software, and a camera I love using.The OnePlus 13 does all this with ease, and I cant ignore that the 12GB/256GB version costs $400 less than the cheapest Galaxy S25 Ultra model, which actually has the same basic specification. Even if youve got $1,299 to spend on a new smartphone, saving that amount of money is the difference between getting a new phone and a smartwatch or smart ring, or just getting a new phone on its own.Samsungs latest phones arent the OnePlus 13s only competition, and the Google Pixel 9 Pro presents a strong challenge too, but that brings me on to another OnePlus 13 strong point. It has AI features, but they arent being pushed as monumentally transformative or as a reason to buy. I love this, as I dont feel like Im paying for features I dont use, as few so far have been all regularly helpful.Perhaps thats also a reason why Ive loved using the OnePlus 13 for the last 84 days or so: its a smartphone, and it absolutely excels at doing smartphone things. I dont really need much more, and if youve been thinking about buying a OnePlus 13, take it from me, someone who is usually happy to swap to a different phone every couple of weeks, you wont regret getting one.Editors Recommendations

The billionaire spoke with The Wall Street Journal ahead of his coming book, Source Code.

In an exclusive excerpt from his new memoir, the co-founder of Microsoft describes his lucky adolescence and his parents support for what he now sees as his own neurodivergence.