Technology

lundi 29 mai 2023

MSI is trying hard to be a premium laptop brand

The MSI Prestige 16 half open seen from behind. — *Here’s the new Prestige 16.* | Image: MSI

MSI — a brand traditionally known for gaming hardware — has announced a bunch of laptops at Computex 2023, and there’s an interesting lack of gamery among them. Instead, the company appears to be focusing hard on the premium lifestyle space with its mid-2023 offerings.

Notable among these releases is the new Commercial 14 series, a line of business laptops intended to compete with high-end enterprise PCs — the likes of the ThinkPad. I conclude this from the fact that MSI’s press release highlights its “tailor-made solutions to enterprises through a series of optional security measures, NFC (near-field communication) and built-in Smart Card Reader.” If that’s not a word-for-word ThinkPad pitch, I don’t know what is.

MSI has attempted business lines in the past, namely in its Summit Series, which we haven’t heard much about for a hot minute. These were solid, functional devices, but they didn’t have the build quality (or laundry list of enterprise security features) to compete with the established top players in that space, and they certainly weren’t priced to do that. The Commercial, which rolls out in the second half of this year, looks like it could be a few rungs up that ladder.

The MSI Commercial 14 seen from the front. — *I won’t lie, it has Summit Series vibes.*

The other release that’s catching my eye is the Prestige 16 Studio Evo, also slated for release in the second half of this year. This is another product laser-focused on the high-end enterprise space. I’ve traditionally thought of the Prestige line largely as productivity devices that also have the chops for some gaming here and there. But this version, as the Studio moniker indicates, is for creative professionals, featuring Thunderbolt 4, a 99Whr battery, and Nvidia’s Studio platform (and RTX discrete GPUs, of course). I’m always on the lookout for powerful devices in the 16-inch space that don’t weigh ten thousand pounds, since big-screened-but-still-portable workstations are a need I hear about from video editors all the time. This Prestige Studio could be a nice get for those folks (if it’s good).

Another big professional product, the Creator Z17 HX Studio, was actually announced earlier this year. It’s geared towards workers across the creative space, from video professionals to digital artists, and it’s compatible with an absolutely bonkers stylus that doubles as a mechanical pencil. MSI has that prominently on display at Computex as well, further pushing the idea that it’s not just a gaming brand, everyone, we promise.

The Creator starts at $2,999 (yeah, it’s not cheap), but MSI hasn’t revealed pricing for the Prestige or the Commercial yet. Those numbers will give us a better idea of where MSI thinks these products fit in the current market and how high-end it thinks they really are.

The Witcher is officially one of the most successful game series of all time

A screenshot from The Witcher 3: Wild Hunt. — Image: CD Projekt Red

The Witcher is a juggernaut, and thanks to new data from The Witcher game developer CD Projekt Red (CDPR), we have a better idea of just how huge it really is. The studio revealed Monday that The Witcher video games have sold more than 75 million copies, with The Witcher 3: Wild Hunt alone responsible for more than 50 million of those sales.

Those sorts of numbers mean that series is one of the biggest video game franchises of all time. For comparison, this new data puts The Witcher 3 in spitting distance of smash hits like Mario Kart 8 Deluxe and Red Dead Redemption 2, which have both sold more than 53 million copies, and both of those are among the top-selling games ever.

Those Witcher sales numbers will probably grow by quite a bit in the coming years. CDPR just released a next-gen update for The Witcher 3 in December, and it has a bunch of other Witcher games in the works, including a remake of the first Witcher game, a new Witcher trilogy, and a spinoff codenamed “Project Sirius” (though CDPR recently announced that it’s reassessing the game).

Let’s just hope those new titles fare better at launch than Cyberpunk 2077, though CDPR has largely turned that game around and released a next-gen patch for it in February 2022. We’ll be hearing a lot more about Cyberpunk 2077 very soon: Phantom Liberty, the game’s upcoming major expansion that stars Idris Elba, will be at Summer Game Fest’s invite-only Play Days event in June, CDPR also announced on Monday.

Netflix is also betting big on The Witcher franchise: it just renewed its Witcher TV series for a fifth season even though the third season hasn’t started streaming yet. The third season will be the last with Henry Cavill starring as Geralt; Liam Hemsworth will take over starting with season four.

WhatsApp is working on usernames and screen sharing

Image: The Verge

WhatsApp is developing a number of new features, including usernames and screen sharing, as reported by WABetaInfo.

The username feature was spotted in the beta version 2.23.11.15 for Android, and allows WhatsApp users to select a unique username attached to their account. The feature could mean that in the future, users could find each other by their username instead of using a phone number. Conversations that are started using a username are end-to-end encrypted, according to WABetaInfo.

Some beta testers using the 2.23.11.19 version of the Android app also noticed a new screen sharing feature. After pressing the screen sharing button, users could confirm and begin sharing the contents of their screen on video calls. The feature also records the portion of the call that is shared, according to screenshots.

Other features rolling out to some beta testers include a “status archive” setting that allows businesses to archive statuses after 24 hours and then reshare them in the future. WABetaInfo notes that the status archive feature so far looks to be limited to businesses.

Computex 2023: all the news from Taiwan’s big PC show

Photo by Sam Yeh / AFP via Getty Images

For one glorious week, PC enthusiasts will gather in Taipei.

After three years, Computex is finally back — in person, in all its glory. The biggest companies in the laptop and PC space, from Taiwan and elsewhere, will be gathered in Taipei this week to showcase products they’ll be releasing this summer and throughout the rest of 2023. We expect to see a whole bunch of refreshes to popular laptop lines, updated desktop components, and maybe even (dare we say it?) a CPU or two. Plus, software services and artificial intelligence were a major focus of CES earlier this year, and we certainly expect that trend to continue.

If you’re interested in following the latest laptop news but can’t make it out to Taiwan yourself, never fear.

We’ll be on the ground in Taipei all week, catching keynotes, interviewing the big players, and getting our hands on some of the most exciting gadgets that you’ll see in 2023. Come along for the ride.

Logi Dock review: conference calls have never been so cute

Power, ports, and pretty lighting — for a price.

I realized two things when the pandemic forced me to start working from home: I suck at hiding the rat’s nest of cables on my desk, and modern laptops don’t provide anywhere near enough ports. Laptop docks have become an indispensable part of most office setups because they solve both of these issues, but not all docks are built equal — nor are they especially stylish.

The $399 Logi Dock goes a step above most. It’s designed as an all-in-one docking solution that allows you to completely ditch microphone headsets and poor-quality audio recording / playback built into laptops during calls. Alongside the additional ports and laptop charging capabilities common on docking stations, Logitech has slapped on some in-meeting controls, a built-in speakerphone, and some funky underlighting. It’s a much jazzier dock than the usual boring slabs handed out in corporate offices.

The Logi Dock can support up to two 4K 60Hz displays while delivering up to 100W of power to a connected laptop, which is enough juice to charge almost anything besides power-hungry gaming hardware. It weighs in at just over two pounds and has grippy rubberized feet to prevent it from sliding across whatever surface it’s placed on. This dock is mostly intended for more permanent office setups, as while it’s light enough to throw into a bag if absolutely necessary, the required power brick is a beast, making it cumbersome to carry around.

Most of the connections are located on the rear of the dock, which is great for keeping your workspace clear of cables. On the back, you’ll find two USB-A ports, two USB-C ports, one HDMI 2.0, and one DisplayPort 1.4 output. These feature alongside the input for the Logi Dock’s supplied 230W power brick, a Bluetooth 5.1 pairing button, a Kensington lock slot, and a dedicated USB-C Upstream (marked with a purple port) that connects the dock to your laptop.

There’s also a third USB-C port located on the side of the dock to spare you from fumbling around the back of the device to plug in any additional peripherals. This particular port and one of the USB-A ports on the rear are marked with a lightning icon to indicate that they support 7.5W fast charging.

Which… well, isn’t exactly “fast” these days. It took around three hours to fully charge my iPhone 14 Pro Max at that speed, and the Logi Dock’s remaining USB ports can only output up to 4.5W. More affordable offerings like the $130 Plugable Docking Station can support 20W of charging on their secondary ports.

A photograph of the Logitech Logi Dock as viewed from the rear, displaying its various ports and connections. — *The Logi Dock doesn’t provide a lot of ports, but it does make the USB-C uplink connection more identifiable by marking it in purple.*

A photograph of the Logitech Logi Dock viewed from the side, displaying a USB-C port. — *Don’t be fooled by the lightning symbol — it represents 7.5W “fast” fast charging, not Thunderbolt.*

The Logi Dock doesn’t provide any Thunderbolt or USB 4 ports, the connectivity standards that can deliver power, high-speed data, and a video signal over a single connection. Instead, all of the USB ports are 3.1 Gen 1 and support meager transfer speeds of 5Gbps. That’s disappointing given the price point, but it won’t be the end of the world for most everyday office workers. Thunderbolt’s biggest advantage is faster data transfer speeds (up to 40Gbps for Thunderbolt 4), so unless you need to optimize your peripheral speeds or frequently move large files of data around, you’ll get by just fine without it.

I have a few port-related gripes out the gate besides the obvious lack of Thunderbolt support. Firstly, none of the USB-C connections support display output, so you can’t hook up a monitor to them. (You have to rely on the HDMI and DisplayPort ports.) The Logi Dock also frustratingly lacks a standard 3.5mm audio jack and an Ethernet port, ports that are commonly found on other docks.

But credit where it’s due — the Logi Dock is visually the best-looking docking station I’ve seen. It’s available in either black or white and features ambient underlighting and a wrap-around fabric skin that’ll complement most modern office setups nicely. It’s the same aesthetic as that used on Logitech’s StreamCam and reminds me of the optional fabric keyboard covers featured on recent Microsoft Surface Laptop generations. The fabric coating didn’t get especially grubby after a few weeks of testing, but that’s something you may want to consider if you’re prone to mess or live with children.

A photograph of the Logitech Logi Dock displaying its reactive under lighting. — *The underlighting is a little difficult to see in bright daylight, but it’s clearer when it turns red after you disable your mic or webcam.*

I’m providing this warning as it’s expected that you’ll be touching it a lot. There is a selection of touch controls across the top of the Logi Dock that can be used to quickly join or leave calls, adjust the speaker volume, and enable / disable your webcam and microphone. Both the webcam and microphone buttons will turn red when disabled. You can also sync the dock with either a Microsoft Office 365 or Google calendar. Doing so enables the Logi Dock’s “one-touch-to-join” feature — the ambient underlighting will turn purple when a meeting is about to start, which you can then immediately join by tapping the circular join button atop the device.

Those controls are supported across Microsoft Teams, Google Meet, Google Voice, Zoom, and Tencent Meeting. I only tested across Teams, Zoom, and Meet, but the controls worked as expected across all of them. There are technically two models of the Logi Dock available — one with a Teams logo as the “join call” button and one with a plain circle. There’s no actual difference between either model besides the design choice, so both will work with any of the supported meeting software.

The audio quality is surprisingly good. You’ll get much better results from dedicated microphones and desktop speakers of course, but the Logi Dock still performs admirably by comparison. There are six beamforming mics built into it (see the small holes on the top) which did a good job of picking up my voice during calls. There were no obvious issues with clarity, though the playback does sound a little crispy.

Results for the “noise cancellation” touted by Logitech were fairly mixed — it completely removed the sound of me smacking my mechanical keyboard and clicking my mouse, for example. It also didn’t create an echo by picking up its own audio output. Some of the household sounds running in the background of calls did manage to come through, though, such as my electric dryer and my neighbors vacuuming.

A top-down photograph of the Logitech Logi Dock displaying its buttons and microphones. — *Those six holes on the top are the Logi Dock’s beamforming mics.*

A photograph of the Logitech Logi Dock, displaying the call buttons on the top of the device. — *The Teams-themed button is just for aesthetics — it’ll also work with Zoom and Google Meet.*

The omnidirectional speakers are suitably loud and clear. I heard some slight interference when audio was playing at a low volume, so I personally wouldn’t want to listen to background music through them while working. At louder volumes, you can hear plenty of bass — I’d liken the quality to something like an old Bluetooth speaker. Otherwise, I didn’t have any difficulty understanding what was being said during calls. I’d advise sticking the dock directly in front of you where possible, as the narrow soundstage can sound a little disorientating when placed to one side.

Bluetooth support is a nice inclusion. You can pair wireless peripherals like keyboards, mice, and headsets to the Logi Dock (though most laptops come with Bluetooth support anyway these days), and you can also connect your phone to it if you want to use it as a speakerphone or Bluetooth speaker. Logitech is pitching this as an in-office solution as much as it is a home one, but let’s be real here — blasting your meeting audio in a busy office for everyone to hear isn’t fun for anyone involved. Don’t be that person.

A photograph of the underside of the Logitech Logi Dock, displaying its rubberized feet. — *There are rubberized feet on the underside, which helps prevent slippage if, like me, you have a tendency to accidentally yank on your peripheral cables.*

There are a few other Logitech-flavored quirks here. The Logi Dock has been designed to play nicely with other products in the Logitech ecosystem — I didn’t have any Zone True Wireless earbuds handy to test the Easy Audio Switch feature, but I was able to easily connect a Bolt-enabled keyboard and mouse through a single Logi Bolt receiver. It’s exactly the sort of ecosystem support I look for when I’m wanting to streamline my work setup.

Which is why I’m still bummed out by Logitech software. You need to install Logi Tune — a program for optimizing Logitech headsets and webcams in meetings — to enable the Logi Dock’s calendar syncing feature. That’s yet another Logitech app clogging up my laptop alongside Logitech Capture, Logitech Options, and Logi Options Plus (yes, really). I couldn’t even install Logi Tune on my work device without permission from a system administrator. That’s not going to be a unique situation and will be especially frustrating when you consider the Logi Dock is targeting working professionals.

A photograph of the Logitech Logi Dock besides its charging brick. — *The power brick for this is MASSIVE, so I’d personally avoid ferrying the Logi Dock around between workplaces.*

Does all of this mean that the Logi Dock is a bad product? Absolutely not. It delivers on pretty much everything it promises. I didn’t have any issues with the peripherals I plugged into it, and it worked just fine with both the M1 MacBook Air and Dell XPS 15 I tested it with (though its worth noting that the M1 MacBook Air can only natively support one external display). It’s reliable, surprisingly compact, and does an excellent job of decluttering your desk. The audio quality is also plenty good enough to appease folks that don’t want to contend with clunky USB microphones or headsets, and it provides more ports and features than similar rival offerings like the $249 Microsoft Audio Dock.

The biggest issue here is that $399 price tag. Omitting both ethernet and Thunderbolt on a dock this expensive feels hard to justify. The lack of a forward-facing IO can also be a nuisance if you frequently switch between a lot of accessories or peripherals, and moving the Bluetooth pairing button to the top or side of the dock would have similarly improved accessibility.

If you can look past those shortcomings and think the idea of a speakerphone conference system combined with a USB hub is appealing, then there aren’t many other options out there. I’m not a convert myself after testing it for a few weeks, but I’m in a committed relationship with my Sony WH-1000XM5 headphones and Rode NT1 XLR mic. The Logi Dock’s audio quality simply can’t compete, and nor do I expect it to. It’s a great choice for those of you who are already looking to minimize your setup and add some additional ports — I’d personally just wait for it to go on sale.

dimanche 28 mai 2023

Watch this Nvidia demo and imagine actually speaking to AI game characters

A cyberpunk ramen shop owner rendered digitally with AI voiceover responding to human input. — *A sample of Nvidia’s ACE (Avatar Cloud Engine) for games.* | Image: Nvidia

At Computex 2023 in Taipei, Nvidia CEO Jensen Huang just gave the world a glimpse of what it might be like when gaming and AI collide — with a graphically breathtaking recreation of a cyberpunk ramen shop where you can actually talk to the proprietor.

Seriously, instead of clicking on dialogue options, it imagines you could hold down a button, just say something with your own voice, and get an answer from a video game character. Nvidia’s calling it a “peek at the future of games.”

Unfortunately, the actual dialogue leaves a lot to be desired — maybe try GPT-4 or Sudowrite next time, Nvidia?

Here’s the entire conversation I hastily transcribed:

Player: Hey Jin, how are you?

Jin: Unfortunately not so good.

How come?

I am worried about the crime around here. It’s gotten bad lately. My ramen shop got caught in the crossfire.

Can I help?

If you want to do something about this, I have heard rumors that the powerful crime lord Kumon Aoki is causing all kinds of chaos in the city. He may be the root of this violence.

I’ll talk to him, where can I find him?

I have heard he hangs out in the underground fight clubs on the city’s east side. Try there.

OK, I’ll go.

Be careful, Kai.

Watching a single video of a single conversation, it’s hard to see how this is any better than picking from a NPC dialogue tree — but the impressive part is that the generative AI is reacting to natural speech. Hopefully Nvidia will release the demo so we can try it ourselves.

The demo was built by Nvidia and partner Convai to help promote the tools that were used to create it — specifically a suite of middleware called Nvidia ACE (Avatar Cloud Engine) for Games that can run both locally and in the cloud.

The entire ACE suite includes the company’s NeMo tools for deploying large language models (LLMs), Riva speech-to-text and text-to-speech, and other bits. It’s also an incredibly good looking demo, of course, built in Unreal Engine 5 with loads of ray-tracing... to the point that the chatbot part feels lackluster to me by comparison. At this point, we’ve simply seen much more compelling dialogue from chatbots, even as trite and derivative as they can sometimes be.

In a Computex pre-briefing, Nvidia Omniverse VP Rev Lebaredian told me that yes, the tech can scale to more than one character at a time and could theoretically even let NPCs talk to each other — but admitted that he hadn’t actually seen that tested.

It’s not clear if any developer will embrace the entire ACE toolkit the way the demo attempts, but S.T.A.L.K.E.R. 2 Heart of Chernobyl and Fort Solis will use the part Nvidia calls “Omniverse Audio2Face,” which tries to match facial animation of a 3D character to their voice actor’s speech.

Dolphin says Nintendo blocked a Steam release of its Wii and GameCube emulator

Image: The Verge

The Steam launch of Dolphin, an open-source emulator for the Wii and the GameCube, has been delayed indefinitely (via PC Gamer). A blog post by the developers says that’s due to a Nintendo “cease and desist citing the DMCA” (an earlier version of the blog post simply said “issued a DMCA” but it has since been updated) after they’d announced plans for a Steam launch in March.

Dolphin Emulator Project:

It is with much disappointment that we have to announce that the Dolphin on Steam release has been indefinitely postponed. We were notified by Valve that Nintendo has issued a cease and desist citing the DMCA against Dolphin’s Steam page, and have removed Dolphin from Steam until the matter is settled. We are currently investigating our options and will have a more in-depth response in the near future.

We appreciate your patience in the meantime.

Pierre Bourdon, who says he was involved with Dolphin for over 10 years in various capacities and named in the email from Valve, writes in a series of Mastodon posts that the notice was the result of a back-and-forth with Nintendo initiated by Steam and involved no DMCA notice, calling the action “just standard legal removals / C&D between two companies.”

One element that may be the point Nintendo is using to justify its request to block Dolphin lies in its distribution of the Wii AES-128 disc encryption, according to Bourdon. Rather than asking users to provide the key on their own, the software has shipped with the Wii’s “common key” embedded in its source code for many years.

Bourdon wrote on Mastodon that, unlike a straightforward DMCA takedown, in this case, Dolphin’s creators have no legal recourse to push back. This leaves the group at the whims of Valve, who he says could have ignored Nintendo at this stage without any repercussions.

We have reached out to Valve, Nintendo, and The Dolphin Emulator Project for further comment.

At least one other emulator, RetroArch, exists on the Steam platform, although that software doesn’t operate quite the same way Dolphin does. Where Dolphin directly emulates the GameCube and Wii consoles, RetroArch serves as a frontend into which emulator “cores” can be loaded, giving users a single centralized place to configure software settings for their emulators.

Quest 3 hands-on confirms Meta’s building a ‘far thinner and lighter’ headset

The Meta Quest 2 sits in a dark room, lit by some purple and blue effect light. — *The Quest 3 will improve on the Quest 2 (pictured above) in many important ways.* | Photo by Owen Grove / The Verge

A hands-on look at the Meta Quest 3 reveals a massive set of improvements to the Meta mixed reality headset, as detailed in Mark Gurman’s Power On newsletter for Bloomberg this morning. Gurman says the Quest 3, now codenamed Eureka, is “far lighter and thinner” than the original Quest 2, which bodes well for its comfort during extended usage.

A lot of the features he mentioned are similar to what we expect to learn about the Apple “Reality Pro” VR / AR headset soon, including fancy hand-tracking and pass-through video. But some rumors say the rumored Apple headset could cost as much as $3,000. Gurman said Meta also hasn’t settled on the Quest 3’s price yet, but that it could be costlier than the $400 Quest 2, which “may stick around at a lower price.” It will still remain far cheaper than the disappointing Quest Pro that launched last fall at $1,499.99 before getting a price cut in March to $999.99.

In February, Meta VR exec Mark Rabkin told employees the Quest 3 would be more expensive than its predecessor and that “We have to prove to people that all this power, all these new features are worth it.” He said Meta had sold 20 million Quest headsets so far.

He also previewed the lighter design, explaining that “The main north star for the team was from the moment you put on this headset, the mixed reality has to make it feel better, easier, more natural... You can walk effortlessly through your house knowing you can see perfectly well. You can put anchors and things on your desktop. You can take your coffee. You can stay in there much longer.”

The report confirms some of the other big improvements we’ve been expecting, like a second-generation Qualcomm Snapdragon XR2 chip, with much better performance overall as a result.

The report also talked about what the Quest 3 won’t have, namely, eye-tracking. That means games can’t use foveated rendering, a feature present in Sony’s PSVR 2 that adjusts based on where a player is looking and allows the system to concentrate processing power on the graphics in those places and pull back elsewhere.

Design upgrades from the Quest 2 include more sensors inside three pill-shaped areas that contain four cameras, two of which are color cameras for passthrough video. It also features an improved system for adjusting the lenses’ inter-pupillary distance — the distance between your eyes — with a wheel you can turn while wearing it instead of taking the headset off and moving the display manually.

A depth sensor in the middle of the device could improve AR performance compared to the Quest Pro’s camera-only approach. Redesigned controllers ditch the Quest 2’s rings, but the depth sensor may help to keep costs down by tracking the controller's position without requiring cameras like the Quest Pro’s controllers. Meta CEO Mark Zuckerberg actually said the Quest Pro would get a depth sensor in a Protocol interview, but the feature didn’t make it to the final version.

Gurman called the pass-through video “almost lifelike,” a good sign after my colleague Adi Robertson called AR mode “murky in low light, washed-out or flickery in bright light, and sometimes luridly saturated in between” in her review of the Quest Pro.

It sounds like improvements there come mainly down to how the headset’s cameras handle light and color, as Gurman didn’t think it looked noticeably sharper, despite rumors of a higher-resolution display.

Right to repair: all the latest news and updates

Broken cracked iphone stock — Image: The Verge

The right-to-repair movement is picking up momentum across the US and the rest of the globe. Here’s the story so far.

Tech companies haven’t always made it easy for consumers to repair their products. Without the manuals, parts, and tools we need, there aren’t many options available, and lobbying paid for by many big companies has worked to keep it that way.

Thankfully, the right-to-repair movement has picked up momentum over the past couple of years, putting pressure on giants like Apple, Samsung, Google, and even John Deere to make it easier for both consumers and independent repair shops to repair their devices. While both Apple and Samsung now have self-repair programs that let customers fix their own devices, there’s still a long way to go to make them more widely applicable, available, and cheaper.

In a handful of US states, lawmakers have signed right-to-repair laws pressing companies to improve the repairability of their products. New York passed a right-to-repair law last year, but it went into effect with amendments that introduced OEM-friendly loopholes. Meanwhile, other states, including Minnesota and Colorado, have been more successful recently in passing right-to-repair laws of their own.

You can catch up on all the latest right-to-repair developments in the stream below.

LG’s 48-inch 4K OLED gaming monitor is over $600 off right now

*LG 48GQ900 48-inch OLED gaming monitor* | Image: LG

The 48-inch LG UltraGear 48GQ900 is on sale at Amazon for an incredible 43 percent off from its typical $1,499.99 price right now, putting it at $852.14 before taxes for Amazon Prime members (or $896.99 for those without Prime), for nearly its lowest price ever. If you’d rather go to the source (or just not Amazon), LG is selling it for $899.99, as is Newegg. This price is as good as it gets for this giant LG OLED gaming display.

If you take this deal, you can expect the usual inky blacks that make OLEDs the contrast champs of the display world, and its 4K resolution will mean a nice, sharp picture spanning its flat panel. Its 120Hz refresh rate can be overdriven to 138Hz, with support for variable refresh rate (VRR), plus stamps for being Nvidia G-Sync compatible and AMD FreeSync Premium. It comes with a nice assortment of ports, too: a DisplayPort port, three HDMI 2.1 ports, two USB 3.2 Gen 1 type A ports, a USB-B upstream port, optical audio out, and a 3.5mm audio jack.

When our own Sean Hollister wrote about this display last year on The Verge, drawing on his experience using the LG C1 as a monitor, he wondered if it has the same aggressive dimming that made the C1 unideal for normal web browsing or office work. Well, the good news is, according to testing at RTings, it doesn’t. The bad news is, it’s because the display’s SDR brightness almost never rises high enough to trigger LG’s Automatic Brightness Limiter, leaving it at a ho-hum 193 cd/m². Still, the outlet gave it high marks for gaming, owing at least in part to its solid HDR performance.

If you insist on repurposing a big ol’ OLED television for office work, there is the 42-inch LG C2, which is just a little smaller, brighter, and is priced the same as the non-Prime member price for the UltraGear at $897. For that price, you’ll get a similar display while losing features like DisplayPort and the ability to overdrive the refresh rate, and of course, you may want to come up with some way to deal with the wide feet it sits on.

For some good tips on picking out the right monitor for working from home, be sure to check out The Verge’s guide.

There’s no telling how long this sale will last, but historically it hasn’t been long, so it may be worth jumping on.

The odd appeal of absurdly long YouTube videos that don’t play anything

An all-black screenshot showing a YouTube video playing a blank screen. — *I swear, this is a screenshot of an actual YouTube video.* | Image: David Pierce

The video’s title is, for once on YouTube, pretty straightforward: “24 hours + of pure black screen in HD!” Leaving aside the questions about the difference between standard- and high-def pure black screens, the video does what it says on the tin. Hit play, and you get more than 24 hours — 24 hours, one minute, 27 seconds, to be exact — of black screen and silence. It’s like turning off your computer, without turning off your computer.

This video has 40.2 million views.

The first time I watched it, I assumed there was a joke or a Rick Roll or something in there somewhere and watched an upsettingly long time to find it. Nothing. So I figured it was a bit. Fun meta-commentary about the drivel people choose to watch! Most commenters seemed to agree and were goofing on the concept. “How is this not in theaters?” commenter Orbital wrote. “The story, the characters, the acting is a masterpiece! especially at 1:23:53, where dark acted as the void, is just so beautiful.” Uinthlees YT called it “a complete masterpiece” with “many wonderful, heart-touching moments.” And Buzzcut Boy wrote that they watch it every night before they go to bed: “i have watched this video so much that i even see it when i close my eyes like my eye lids are a little screen playing this master peice.”

But now, after spending too many hours watching too-long videos just like “24 hours + of pure black screen in HD!” I think I’ve discovered their true purpose. Not only are they not a joke but they’re also some of the most useful and user-friendly things on YouTube.

The ultra-long video is a longtime staple of YouTube, of course. The first one I remember watching was 10 hours of goats bleating the chorus to Taylor Swift’s “I Knew You Were Trouble,” but I think my all-time favorite is when Nathan Graham from the gaming channel Unspeakable uploaded a video called “PLAYING MINECRAFT FOR 24 HOURS STRAIGHT!” which turned out to be a few minutes of gaming and about 23 hours of looped footage of Graham sleeping. The upshot: 14 million views. It’s a good joke.

There are more useful genres of mega-long YouTube, too. You can get 24 hours of a roaring fire, which is good background viewing in the winter. There’s an astonishing amount of content directed at dogs, which mostly amounts to 20-plus hours of soothing music and nature shots. (The “most replayed” bit of one such video is a sweeping overhead shot of a lush island, down to the beach, and I like imagining my dogs just scrubbing back to that bit over and over to soak in the island vibes.) There’s also plenty of super-long Cat TV, too, but that seems less popular. I found one that’s just 20 hours of a seal spinning around in the water, titled “No need to be Upset 20 HOURS LONG!!” It has 644,000 views, several of which are now me.

The most sensible long videos are the music ones. Twenty hours of spa music, 12 hours of jazz, 14 hours of loungey covers of popular hits. I’ve come to like these even better than the always-streaming channels like Lofi Girl because they’re so predictable — I’ve played a 24-hour video called “Starbucks Jazz Music Collection 2021 - 24 Hours Smooth Jazz for Studying, Work, Relax, Sleep” so many times that my brain knows its ebbs and flows, and it barely even registers as I go about my day.

And yet, I still can’t explain why “24 hours + of pure black screen in HD!” is such a huge hit. Its channel’s owner, a guy named Noah who calls himself “Black Screen Guy,” has picked up 65,000 subscribers and more than 150 million views on videos just like it. The even longer “44 hours of pure black screen in HD!” has 5.4 million views. Thirty-five hours, 2.2 million views. Thirty-two hours, 2.4 million. The channel’s most surprising success story? “24 hours of pure white screen!” is exactly what it sounds like and has 44 million views. Which is a lot more than the 7.2 million on “a red screen for 24 hours!”

In this case, it turns out, the outrageous length is the whole appeal. Across all these videos and many other silent blank ones, every viewer seems to have their own use case. The most common, by far, is to use these videos as a way to simply keep your device on. “I keep this playing overnight so that my laptop doesn’t shutdown while downloading games,” one commenter wrote. “I have to keep this open on my phone because it’s broken and will not turn back on if it turns off,” another said.

There are also a surprisingly large number of times when you might want your device on but the screen off. “I use this so I can have music open on another tab at night and have this open so the screen with the music on it wont shine so bright in my room,” one commenter wrote on a two-day-long video of a blank black screen. “I use this every night, put on a podcast and q this to come on next,” said another. “Unironically useful for avoiding screen burn in,” another wrote. “Big thanks <3.”

In the description of one video, a 10-hour saga of pure black screen, the Black Screen Guy himself suggested even more possibilities. You can use a black screen to check your computer’s backlight or look for dead pixels; to trick your parents into thinking the computer’s off so you can play games without having to reenter the password; to track time by how long the video’s been playing; to clean your screen without turning off the computer; and so much more. A black screen does wonders, apparently, especially when it doesn’t involve turning anything off.

My immediate reaction to this was, well, confusion. Just turn off your screen! You can change the settings on a Mac or a PC to turn off your display without putting your computer to sleep, and smartphones and tablets have plenty of ways to play audio in the background even with the display off.

But you know what’s actually easier than tweaking a bunch of settings, especially for younger users accustomed to finding everything they need on YouTube? Just playing a video. One commenter on a blank-screen video called it “the perfect video to cast to your tv when you’re too tired to get up and turn it off,” which seems both ridiculous — if you can cast from your phone to your TV, you can probably use your phone to turn off your TV! — and telling. A blank-screen video is both a stupid solution and a strangely elegant one.

In a way, I’ve come to see “24 hours + of pure black screen in HD!” as a perfect microcosm of YouTube. YouTube is part entertainment platform, part information library… and part tools repository. It can soundtrack your day, teach you how to beat any game or solve any problem, keep your pets entertained while you’re gone, or transport you to just about any place on earth. A blank screen video is a productivity tool, plain and simple.

I even understand now why a seven-day-long video, which is just a timer counting down 168 hours, has 3.7 million views. One commenter summed it up thusly, “This is the timer you need when you need to stay active on your computer while working from home. No one will notice you were gone because this video keeps playing.” As long as the computer’s awake, I can be wherever I want.

samedi 27 mai 2023

Apple’s $50 million butterfly keyboard settlement is finally approved

Picture of a MacBook with butterfly keyboard. — People who owned MacBooks with butterfly keyboards will now get paid. | Photo by Vjeran Pavic / The Verge

The $50 million settlement over Apple’s bad butterfly keyboard design got final approval by a federal court judge in California, Reuters reported yesterday.

US District Court Judge Edward Davila denied an attempt to amend the agreement, writing in his ruling that 86,000 people filed claims. That finally puts a figure on the number of people affected who will get compensation for repairs they’d paid for. Or at least the number who heard about the lawsuit and followed it to the settlement agreement that was reached last July.

The original suit came about because Apple laptops from 2015 to 2019 had a new keyboard design that just didn’t hold up under normal use; crumbs and dirt, or even just accumulated dust, could cause keys to fail or stick. Casey Johnston famously wrote in The Outline that “The new MacBook keyboard is ruining my life.”

Despite Apple’s repeated attempts to iterate on the keyboard, the problem didn’t go away until it released the 16-inch M1 MacBook Pro in 2019, which took things back to the “scissor switch” design that also ships in the Magic Keyboard for Apple desktops. The design was fully phased out of its products a few months later when Apple released a redesigned 13-inch MacBook Pro. Apple’s settlement doesn’t include an admission of wrongdoing but will pay some people back up to $395 to cover their repair costs.

This final wrinkle in the saga involved six objectors who offered arguments saying the settlement wasn’t fair to MacBook owners who’d never repaired their failed keyboards (and therefore don’t get any cash) or that the $125 offered to those who’d only had to pay for one replacement wasn’t enough to cover the cost of repairs. But Davila denied their objections, saying that just wanting more money isn’t enough to deny the settlement’s approval.

In short, anyone who filed a verifiable claim for keyboard money by the March deadline will be getting their money soon.

Apple’s entry-level MacBook Air is down to its all-time low at Amazon

An M1 MacBook Air laptop from Apple opened on a desk. — *Apple’s entry-level MacBook Air is an easy rec at $799.99 thanks to its speedy performance and long-lasting battery life.* | Photo by Vjeran Pavic / The Verge

Happy Saturday, readers! Apple’s upcoming Worldwide Developer Conference (WWDC) is now less than two weeks away. The company is largely expected to introduce its mixed reality headset — ending what feels like a decade of rumors — along with a new 15-inch MacBook Air. However, if you’re looking for a 13-inch machine that packs plenty of value, Apple’s base MacBook Air from 2020 is matching its all-time low of $799.99 ($200 off) at Amazon and Best Buy.

Despite its age, Apple’s M1-equipped remains one of our go-to recs for anyone who can’t afford the newest MacBook Air but wants something lightweight and relatively fast. We once heralded it as one of the best laptops you could get, namely due to its long-lasting battery life, solid keyboard, and the strength of Apple’s M1 silicon, which continues to hold up even if the last-gen Air can’t quite compete with newer models. It’s not a budget buy, per se, but if you want an everyday machine for work and entertainment, you’d be hard-pressed to find one that offers more value for the money.

Read our M1 MacBook Air review.

Streaming devices might not literally be a dime a dozen, but, suffice it to say, there are a lot of fantastic options to consider when you’re on the hunt for your next streamer. Most of them aren’t anywhere near as versatile as Amazon’s third-gen Fire TV Cube, though, which has hit an all-time low of $119.99 ($20 off) at Amazon, Best Buy, and Target.

At its core, the latest Fire TV Cube is a streaming device that also pulls double duty as a smart speaker thanks to an array of beam-forming mics. Much like the Fire TV Stick 4K Max, it supports Wi-Fi 6E and 4K streaming in all the popular HDR formats (including Dolby Vision), yet it also touts faster performance and support for hands-free voice commands, which are now far more capable than they were just a few years ago. Now, pair the aforementioned specs with the speaker’s built-in HDMI input and attractive, fabric-adorned and you have a streaming device that’s a real step up from Amazon’s budget offerings.

Read our Amazon Fire TV Cube (third-gen) review.

Peacock may have dropped its free membership tier in February, but there are still ways to save on the streaming service if you know where to look. Now until June 12th, for example, new and returning subscribers can grab a year of Peacock Premium for $19.99 ($30 off) when they use promo code SUMMEROFPEACOCK.

If you’re curious as to how Peacock’s two subscription plans differ, well, there isn’t much to know. The ad-supported Premium plan gives you access to all of the same movies and TV shows as the higher tier — meaning you can still use it to burn through Cocaine Bear, Rian Johnson’s oh-so-excellent Poker Face, and whatever the hell Vandepump Rules is — along with select sporting events and news. You won’t get as much live programming or the ability to download content for offline viewing, but, hey, it’s also less than $2 a month.

A few more deals for your Memorial Day weekend

Anker’s MagSafe-ready 622 Magnetic Battery is still on sale at Amazon for $39.99 ($30 off) when you clip the on-page coupon for an additional $10 off. Anker is offering the same discount through May 28th with promo code WSCPJQTUSS, making now a good time to pick up the 7.5W magnetic charger. Read our magnetic charger buying guide.
The AirPods Max, Apple’s luxe on-ear headphones, have returned to $449.99 — about $100 off and their second-best price to date — at Amazon, Best Buy, and Walmart. The wireless headphones certainly aren’t cheap, though they do showcase phenomenal build quality, great noise cancellation, and the kind of simplicity for which Apple has become known. Now, if only the included carrying case wasn’t such a travesty. Read our review.
The Razer Huntsman Mini is currently on sale at Amazon with clicky optical switches for $69.60 (about $50 off). Although the wired 60 percent board is one of Razer’s smallest, it still features programmable macros and RGB backlighting, which you can customize with Razer’s Synapse software.
We aren’t going to wax too poetic regarding Vizio’s M512a-H6, but if you’re looking for a powerful soundbar with up-firing speakers and support for Dolby Atmos surround sound, you can pick it up on Amazon with a 6-inch sub and two rear speakers for $374.43 (about $126 off). Read our soundbar buying guide.
The fifth-gen Echo Dot is still down to $39.99 ($10 off) at Amazon and Best Buy. It remains to be seen how the latest Dot compares to Amazon’s newest Alexa speaker, the Echo Pop, but we do know the Dot retains some hardware advantages over the latter. This includes a temperature sensor and an option for an LED clock, one that can display the time, weather, song titles, and other helpful tidbits of information. Read our review.

Somebody cracked Windows XP activation for offline use

Bliss XP wallpaper — *Windows lives on.* | Image: Microsoft

The activation algorithm for Windows XP has, incredibly, finally been completely cracked, allowing for totally offline activation, according to The Register (via Ars Technica). A blog post on tinyapps covered a Reddit post discussing it, but the program allowing it has apparently existed for at least several months, possibly floating in the ether as a torrent download.

As for who created the software, nobody in the subreddit post knows, including user retroreviewyt, who first shared it and isn’t even sure where they got it from, speculating it came from from a torrent somewhere.

In the meantime, someone appears to be working on reverse engineering the software. A user calling themselves Neo-Desktop dropped the program into Github and said in a discussion there that they are working to create an open source version.

Microsoft ended official support for Windows XP just over nine years ago, but the OS refuses to die. In fact, as recently as 2021, the Windows XP remained the most popular operating system in Armenia. And in 2019, Forbes detailed a study by SpiceWorks that found one in three US businesses still had at least one Windows XP machine on their networks.

That’s forced the company to issue security updates when something bad enough comes along. Remember WannaCry? Windows XP got a patch against that in 2017. A similar exploit prompted another one in 2019.

What training with the Apple Watch Ultra taught me about multiband GPS and failure

An illustration of a GPS indicator, a fitness app, and a jogger, each with a number in front of them, standing in a lineup within an Apple Watch. — Illustration by Hugo Herrera for The Verge

It’s easy to blame trackers when fitness goals don’t go according to plan, but sometimes the problem lies closer to home.

I almost quit this year’s New York City Half Marathon.

The moment is seared into my brain. I’d been running for nearly two hours in freezing temperatures, straight into the wind. The Apple Watch Ultra on my left wrist buzzed to tell me I’d just passed mile nine. On my right wrist, the Garmin Forerunner 265S said I’d only run 8.55 miles. A short-ish distance ahead, I could see the official mile nine marker. I had no idea which distance was “true.” It didn’t matter, though. All I wanted was to beat last year’s time, even by just one millisecond. That had felt like an achievable goal. I’m no math whiz, but what I saw on the official clock meant I’d have to run the last four miles at Eliud Kipchoge-level speeds to match last year’s time. That wasn’t just unachievable. It was impossible.

I broke. If it weren’t for a well-timed cheer from a friend around mile 10, I probably would’ve called it a day. I’m really not sure how I powered through the rest of the race; something inside me died at the finish line. (The watches didn’t die, though; the race barely made a dent in the Ultra’s battery, and that was without any low-power settings.)

Whatever it was, it left a gaping hole that no finisher’s medal could ease. I hadn’t missed my goal by one or two minutes. I was a whole 13 minutes slower than last year. None of it made sense. Sixteen weeks of consistent training should’ve been more than enough for a race I was familiar with. So after 48 hours of moping, I set out to find out what had killed my half-marathon dreams.

Suspect one: GPS

You’re guaranteed to see GPS watches at any road race. In outdoor running, GPS watches help you calculate pace and distance, both of which are crucial when training. The more accurate your GPS watch, the easier it is to trust the results of your training. Maybe I whiffed it on race day because the stars and satellites were misaligned.

Its superior GPS is one reason I picked the Apple Watch Ultra as my primary training watch for the NYC Half. (That and I wanted to spend more time with the new running form metrics in watchOS 9.) Not only is the Ultra geared toward endurance athletes but it’s also one of a handful of smartwatches that have dual-frequency GPS.

The appeal of this new-ish technology is that it’s supposed to deliver next-level accuracy. While I’d been running with the Ultra since it launched, I’d yet to see how it stacked up against a Garmin on longer distances over an extended training period. On my spare wrist, I alternated between the Garmin Fenix 7S Sapphire Solar and Forerunner 265S, which also have dual-frequency GPS, for my long runs. (I’d have done it for the entire 16 weeks, but the plight of a smartwatch reviewer is you have to keep one wrist free at all times for new products.)

Looking back at the data, the Ultra and both Garmins delivered similar results during training. At most, I’d see a difference of maybe a tenth of a mile. That wasn’t the case on race day. The Ultra recorded 13.42 miles, while the Forerunner reported 12.92 miles. Neither of those distances is 13.1 miles, which is the official length of the course. And yet, the maps generated by both were nearly identical. Clearly, something had happened that day. While I consider myself well versed in the practicalities of GPS watches, I wanted to talk to an expert about what happened. So I asked Apple to get into the nitty-gritty of how the Ultra’s multiband GPS works — and why my data was so different on the day it mattered most.

I expected Apple to launch into why the Ultra’s GPS was leagues ahead of the competition’s. To be fair, every smartwatch maker will tell you their GPS tech is the best. That said, I was surprised that the Ultra (plus the Series 8 and SE) doesn’t rely on GPS alone.

“A product like this, that also has network connectivity, enables us to use the entire system in ways that traditional GPS systems can’t,” says Rob Mayor, Apple’s director of motion and location technologies.

Close-up of the Apple Watch Ultra — *This thin gray metal band is what enables the Ultra to access the L5 frequency.*

Traditional GPS requires downloading a satellite’s estimated position in order to begin tracking. That can create challenges if you’re in an obstructed environment. Signals can be corrupted, take more time to download, or get blocked by objects like skyscrapers, canyons, or tree foliage. Mayor says the Ultra can cache orbit predictions for up to a week. That means you can go offline and still get an immediate location fix because you don’t need to wait for your watch to decode that information; it’s already there.

Similarly, if you fly to another state for a race, the Ultra doesn’t have to go fishing in the sky for the correct satellites. According to Mayor, the watch can acquire GPS more quickly by tapping into Apple’s database of Wi-Fi access points to get a rough idea of your location and figure out which satellites to look for. Maps data also plays into the equation. While most people in the US think of Maps directions in the context of driving, this hybrid approach can help put pedestrians on the right cycling, hiking, or running route — especially in cities. Basically, that extra Maps data ensures your route summary isn’t going to say you’re running through a river or magically ghosting through buildings.

Altogether, the additional L5 signal is cross-referenced with data from Maps and Wi-Fi for what Mayor calls hyper-accurate GPS. It’s important to maintain a healthy skepticism, but it’s hard to argue that this method doesn’t deliver freakishly accurate location data. For instance, the Ultra (plus Series 8, SE, and any watch running watchOS 9) can automatically detect when you arrive at a running track. It also knows which lane you’re running in without calibration. If I hadn’t tried it out myself — multiple times, mind you — I’d be inclined to think it’s too good to be true.

But even if the Ultra uses a blend of tech, it doesn’t piggyback off your phone’s GPS as previous Apple Watches did. Mayor told me the Ultra has gotten to the point where your iPhone’s signal doesn’t add much.

Smooth GPS line from Ultra — *I can definitely see the benefit of Maps data here from my race.*

Close-up of Garmin route data, but it’s more squiggly than the Ultra’s. — *My Garmin data is also still pretty good, but it’s possibly a bit tripped up by tall skyscrapers in Times Square.*

That still didn’t answer why such high-tech devices with fancy GPS gave me results that didn’t match up with the official course. It’s something that I’ve noticed at multiple races, and after my half-marathon debacle, I wondered if this “miscalculation” had in some way left me underprepared.

“A lot of people don’t understand how they map and measure race courses. They assume they’re going to cross the finish line at exactly 13.1 [miles] or 26.2 [miles],” Eric Jue, director of Apple Watch product marketing, told me after I relayed my NYC Half tale. “And they’re a little bit discombobulated when they see something different.”

As it turns out, you’ll run at least 13.1 miles in a half-marathon. The official distance is based on the most optimal route and doesn’t account for zigzagging through other runners, running toward the sides of the road, or stopping at water stations. Most people don’t run the most optimal route and end up running a bit more. By that reasoning, you could argue that the Ultra’s 13.42 miles is closer to what I actually ran than is the Forerunner 265S.

“I think that users’ perceptions [are] like, here, I have this thing that’s very precise and I’m comparing it to things that are potentially less precise, as well as my perception — which is probably less precise as well,” agrees Mayor. “It’s a confluence of those things.”

Okay, okay. It wasn’t the GPS.

Suspect two: training data and features

A couple of weeks later, I found myself at McCarren Park Track in Brooklyn. It was a chilly, overcast day, and I tried to stay warm hopping from one foot to the next. Apple had invited a gaggle of journalists out to demo watchOS 9’s running features. I’d used them before while reviewing the Ultra, but I hoped a refresher would reveal something I’d missed during my own training.

We ran around 3.5 miles, broken up into several shorter runs. Apple had us try the custom workouts, which let you program running routines, including intervals and pace targets, on the watch, while Fitness Plus trainer Josh Crosby demonstrated how certain alerts for heart rate zones, running power, and pace worked. I ran multiple laps around the track, which again highlighted the Ultra’s eerily accurate GPS. But of all the running features, the one that “bothered” me most was the pace alerts.

The feature itself is self-explanatory. Set a target pace — or a pace range — and then run. Whenever I ran too fast or too slow, the Ultra would buzz on my wrist. You’d think, after all these years, I’d have a good sense of what my 10-minute mile feels like versus an 11- or 12-minute mile. You’d think I’d be good at maintaining a consistent pace — a vital skill for running a long-distance race.

Apple Watch Ultra on wrist prompting user to pick a lane after arriving at a running track. — *Maps data can help zero in on the exact track lane you’re running in as well as make sure your map doesn’t have you running through buildings.*

Turns out, I wasn’t. At least, not that track day. I kept getting alerts that I was slipping in and out of my target ranges. After a few loops at what should have been an easy pace, I found myself breathing harder than normal, wondering why it felt like I was running through molasses even though 3.5 miles was well within my wheelhouse. I thoroughly enjoyed myself, but afterward, that heaviness and the alerts lingered in my mind. Is this what a 10:30 pace really felt like these days? Had I inadvertently underestimated my pace during those 16 weeks with sporadic, intermittent checks?

For my half-marathon training, I only occasionally dabbled with these features. I mostly stuck to a training plan I’d found in Runner’s World. After the day at McCarren, I felt inspired to go all in on the watchOS 9 running features on the Ultra. Custom runs with pace alerts, racing my previous times on common routes, engaging more with the metrics mid-run — you name it, I tried it over the course of a month. I figured I should see some improvement. At the very least, I would have a trove of data to pore over to see if any patterns emerged.

I learned three things. First, I’m not a competitive person. Racing my time on past routes was a unique kind of torture. Second, I’m not as good as I thought at regulating pace for runs that are over an hour long. And third, I was getting slower. Slower! Before you ask if I added strength training and proper recovery during and after half-marathon training — yes, I did.

It’s tempting to lay the blame on the Ultra (and all my other wearables). But the Ultra’s GPS maps continued to match what I got on my iPhone and my Garmin watches. My heart rate matched my Polar H10 strap. My sleep data wasn’t as accurate as the Oura Ring, but it wasn’t too far off either. If I’m honest with myself, I knew none of these devices were at fault.

After a month, I was at a loss. So I gave up. I pared down the Ultra’s running features to custom workouts and put on pace alerts for speed work only. (Mainly so I wouldn’t go too fast out the gate.) I stopped scrutinizing my workout summaries. As it turns out, as soon as I put some boundaries in place, I finally, finally started to improve.

I’d used the features properly — and they’d worked as advertised. The data was reliable. I improved as soon as I stopped trying so hard. I didn’t like what that meant, but it’s like Sherlock Holmes says. Once you eliminate the impossible, whatever remains must be the truth.

Suspect three, and the culprit: me

All I wanted from this year’s NYC Half was to run it faster than last year. I wanted that because, last year, I ran the race — my first half-marathon — as part of Team ALS. I joined on a whim mere weeks after my mom died from the incurable disease. It felt like rebellion after a year defined by ALS. I had about six weeks of real training, and going from zero to 100 like that was... an experience. Four of my toenails fell off, and I honestly don’t remember much of the race itself. But just as I’ll never look at 2021 without thinking of ALS, I’ll never look back at 2022 without feeling my grief. I wanted to run the 2023 NYC Half Marathon for myself, and without realizing it, I planted the seed in my head that doing well would mean I was finally okay.

Unfortunately, it doesn’t work like that.

Loss is exhausting, and I feel most free from its grip while running. Viewed from that lens, I suppose it’s obvious that I’d turn to the Ultra and its training metrics so that I could run the best race of my life. I could list a dozen valid reasons why that didn’t pan out, but I’ve come to accept that, at the heart of it, I didn’t really want to do better this year. Part of me wanted to tie up this chapter of my life with a pretty, symbolic bow. To move on to what’s next. The rest of me isn’t ready.

The thing about wearables — and people — is that they assume health can be measured. If you can read the metrics the right way, if you can interpret the data, then you can compare who you were to who you are becoming. Among smartwatches, the Ultra is a magnificent beast. But for all the impressive tech it packs in its titanium case, it cannot measure grief. Mental health is also health, and as they say, the body keeps the score. It just so happens that the mental side of the equation is much harder for wearables to meaningfully quantify.

It seems silly to spill this much ink over a botched race, but technically, this is how wearables are supposed to work. You collect data over a period of time. Depending on your progress (or lack thereof), you learn something about yourself. We just anticipate that progress to be a linear, ever-rising line. Growth is annoyingly not linear, and facing failure isn’t pleasant. I can’t say these are the lessons I wanted to learn, but I’m grateful for them nonetheless.

All that’s left is to take these lessons and apply them going forward. I’ve already signed up for my next race. I will 1,000 percent be testing no less than four devices — including the Ultra — while training. But for once, I have no time goal. I’m trying not to make a narrative of the data. I think I’ll simply run and see what that feels like.

How to watch Nvidia’s Computex 2023 keynote (and what to expect)

Image: Future Publishing via Getty Images

Computex, one of the biggest trade shows of the year for the laptop and PC space, begins in a couple of days. A number of companies will have big announcements, but the most anticipated event of the week is Nvidia’s keynote, which will open the show on Monday morning.

The keynote speaker will be Nvidia’s founder and CEO Jensen Huang, who — in case you missed it — added $7 billion to his net worth a few days ago following the company’s massive Q1 earnings report.

Nvidia hasn’t publicly released much information about the topics Huang will cover; Computex revealed that the talk would include “advanced developments in the fields of accelerated computing and artificial intelligence.” Needless to say, we expect AI to feature heavily. Nvidia’s technology helps to drive popular generative AI products like ChatGPT and Bard. This year’s chatbot explosion has driven unprecedented growth for the company, including what some have called the all-time largest one-day increase in a firm’s valuation.

Rumors have also been swirling that we might see new graphics cards announced. This is looking less likely since the company’s RTX 4060 family of GPUs just hit shelves earlier this week. Still, you never know — it’s possible we could get a sneak peek of more powerful hardware to come.

The fact that the show takes place in Taiwan means that folks in North America will need to stay up late to catch the live event. But if you’re bored after the Succession finale or just happen to be a night owl, you can catch the keynote on YouTube (or right here). It goes live on Monday, May 29th, at 11AM in Taipei, which is Sunday, May 28th, in the US at 8PM PT and 11PM ET. If you’re the sort of person who doesn’t regularly attend technology keynotes at late hours, you’ll also be able to catch a replay on YouTube.

Following the keynote, Nvidia VP of corporate marketing and developer programs Greg Estes will also be giving a talk called “Racing Towards the Industrial Metaverse,” which will cover “how NVIDIA and its partners are using Omniverse, generative AI, and accelerated computing to enable an exciting new era of 3D workflows.” This will take place on Tuesday, May 30th, at 2:30PM in Taipei. It doesn’t look like this will be livestreamed, but a replay will be available, and you can sign up to be notified when that goes live on Nvidia’s website.