SoylentNews

takyon writes:

Google will shut down its Stadia cloud game service on January 18, 2023. All Stadia hardware and software purchases made through Google will be refunded:

Stadia's technology will live on as a Google Cloud product called "Immersive Stream for Games." Google has made some headway pitching the feature as a way to run games on underpowered devices, like Peloton fitness equipment.

Google Stadia never lived up to its initial promise. The service, which ran a game in the cloud and sent each individual frame of video down to your computer or phone, was pitched as a gaming platform that would benefit from Google's worldwide scale and streaming expertise. While it was a trailblazing service, competitors quickly popped up with better scale, better hardware, better relationships with developers, and better games. The service didn't take off immediately and reportedly undershot Google's estimates by "hundreds of thousands" of users. Google then quickly defunded the division, involving the high-profile closure of its in-house development studio before it could make a single game.

Competitors include Nvidia's GeForce Now, Xbox Cloud Gaming, and Amazon Luna.

See also: Stadia controllers could become e-waste unless Google issues Bluetooth update
Stadia's technology will go on to do greater things, but no one really cares anymore
Stadia died because no one trusts Google

Previously: Google Announces "Stadia" Streaming Game Service
Google Details Pricing, Hardware for Stadia Streaming Game Service

Original Submission #1   Original Submission #2

hubie writes:

An AI Message Decoder Based on Bacterial Growth Patterns:

From a box of Cracker Jack to The Da Vinci Code, everybody enjoys deciphering secret messages. But biomedical engineers at Duke University have taken the decoder ring to place it's never been before — the patterns created by bacterial colonies.

Depending on the initial conditions used, such as nutrient levels and space constraints, bacteria tend to grow in specific ways. The researchers created a virtual bacterial colony and then controlled growth conditions and the numbers and sizes of simulated bacterial dots to create an entire alphabet based on how the colonies would look after they fill a virtual Petri dish. They call this encoding scheme emorfi.

The encoding is not one-to-one, as the final simulated pattern corresponding to each letter is not exactly the same every time. However, the researchers discovered that a machine learning program could learn to distinguish between them to recognize the letter intended.

"A friend may see many images of me over the course of time, but none of them will be exactly the same," explained Lingchong You, professor of biomedical engineering at Duke. "But if the images are all consistently reinforcing what I generally look like, the friend will be able to recognize me even if they're shown a picture of me they've never seen before."

[...] Give the cypher a try yourself. You can type in anything from your name to the Gettysburg Address, or even the Christmas classic, "Be sure to drink your Ovaltine."

https://www.patternencoder.com/

Journal Reference:
Jia Lu, Ryan Tsoi, Nan Luo, et al. New encryption method uses simulated bacterial growth based on specific initial conditions to form patterns corresponding to letters [open], Patterns, 2022. DOI: 10.1016/j.patter.2022.100590

Original Submission

Arthur T Knackerbracket has processed the following story:

In 1918, the steam-powered SS Mesaba sank in the Irish Sea after being hit by a torpedo from a German submarine during World War I. The ship might have been forgotten, except that it had ties to the infamous Titanic disaster of 1912. On Tuesday, Bangor University announced that the shipwreck of the Mesaba has been located.

Mesaba was a merchant vessel traveling in the same waters as the Titanic. According to the Encyclopedia Titanica, a repository of Titanic research, the Mesaba sent the large passenger ship a radio message cautioning of heavy pack ice and a great number of large icebergs. The message, however, was never relayed to the Titanic's bridge. The Titanic struck an iceberg and sank later that evening, in a disaster that claimed more than 1,500 lives.

The research team found the Mesaba among 273 shipwrecks scattered across 7,500 square miles (19,400 square kilometers) of the sea. The researchers used an advanced seafloor mapping technology called multibeam sonar and combined the results with historical records and maritime archives to identify the merchant ship's final resting place. A dramatic sonar image shows the Mesaba split into two main parts.  

Original Submission

upstart writes:

New Regulations Will Force Airlines to Refund Air Travelers for Broken Wi-Fi - ExtremeTech:

Air travel must often be approached with the same attitude you'd bring to a game show: wary yet eager as you throw caution to the wind and embrace the unknown in the name of a new adventure. Maybe you'll have a good experience, with straightforward ticket prices and working in-flight Wi-Fi; maybe you'll lose everything at the last minute, having been hit with a canceled flight just moments after unexpectedly having to pony up for a checked bag. A lack of airline accountability can make for a whirlpool of exasperating (and financially painful) circumstances. Soon, this could change, as yesterday the White House proposed a slew of regulations that would protect air travelers from shady airline practices.

First up on the docket would be disclosing flight-related fees upfront. As of now, you often don't see extraneous fees until you go to pay for a flight. Other times, it's not clear what fees might be charged to change your flight, or you could get to the gate without ever having learned the cost of sitting with your child. The White House's new rule would require that airlines and travel search websites "disclose upfront—the first time an airfare is displayed—any fees charged to sit with your child, for changing or canceling your flight, and for checked or carry-on baggage."

A second proposed rule would require airlines to refund travelers for in-flight Wi-Fi that they purchased but couldn't use. (Yes, you read that right: airlines can currently charge you for internet connectivity, fail to provide it, and then refuse to give you a refund.) Though only Wi-Fi was named in the US Department of Transportation's press release, the rule would also protect other services purchased yet never fulfilled.

What sort of fees have you unexpectedly been hit with on a flight?

Original Submission

takyon writes:

Bruce Willis sells deepfake rights to his likeness for commercial use

Bruce Willis has sold the "digital twin" rights to his likeness for commercial video production use, according to a report by The Telegraph. This move allows the Hollywood actor to digitally appear in future commercials and possibly even films, and he has already appeared in a Russian commercial using the technology.

Willis, who has been diagnosed with a language disorder called aphasia, announced that he would be "stepping away" from acting earlier this year. Instead, he will license his digital rights through a company called Deepcake. The company is based in Tbilisi, Georgia, and is doing business in America while being registered as a corporation in Delaware.

Deepcake obtained Willis' likeness by training a deep learning neural network model on his appearances in blockbuster action films from the 1990s. With his facial appearance known, the model can then apply Willis's head to another actor with a similar build in a process commonly called a deepfake. Deepfakes have become popular in recent years on TikTok, with unauthorized deepfakes of Tom Cruise and Keanu Reeves gathering large followings.

Original Submission

upstart writes:

New Hubble and Webb Images Capture Aftermath of DART Asteroid Smash Up:

The event marked the first time that Hubble and Webb simultaneously observed the same object.

NASA's first attempt at nudging an asteroid from its usual orbital path was captured by the DART spacecraft itself, its companion spacecraft, LICIACube, and various ground-based observatories on Earth. And as promised, the celestial smash up was also observed by the Hubble and Webb space telescopes, the first images from which were released today.

The recently commissioned Webb Space Telescope captured one image of the Didymos-Dimorphos system before the collision and several in the hours after the event. In total, Webb performed five hours of observations, capturing 10 images. Astronomer Heidi Hammel from the Association of Universities for Research in Astronomy led the viewing session.

[...] The newly released Hubble image shows plenty of surface material emanating from Dimorphos, with rays extending out from its body. Some of the rays have a slight curve to them, which astronomers will need to study and explain. Fascinatingly, the brightness of the Didymos-Dimorphos system increased three-fold after the impact, and this brightness held steady for eight hours. Again, this is something astronomers will need to explain.

Hubble will perform 10 more observations of the system over the next three weeks. "These regular, relatively long-term observations as the ejecta cloud expands and fades over time will paint a more complete picture of the cloud's expansion from the ejection to its disappearance," the ESA release stated.

Original Submission

Snotnose writes:

Saudi Arabia's government-funded gaming conglomerate The Savvy Gaming Group will invest $37.8 billion in gaming as part of a controversial effort to expand the kingdom's role in the sector.

Savvy has earmarked more than $13 billion "for the acquisition and development of a leading game publisher to become a strategic development partner," according to the kingdom's press agency.

From Reuters we read:

Saudi Arabia's Savvy Games Group, owned by sovereign wealth fund PIF, will invest 142 billion riyals ($37.8 billion) in initiatives aimed at making the kingdom a global hub for gaming, state news agency SPA said on Thursday.

The investments will include 70 billion riyals to take several minority stakes in companies that support Savvy's game development agenda and 50 billion riyals to acquire "a leading game publisher to become a strategic development partner".

Another 20 billion riyals will be invested in mature industry partners who bring expertise to Savvy's portfolio and 2 billion riyals will target industry disruptors "to grow early-stage games and esports companies."

Not seeing how making video games passes my 7th grade "this is what your government does" chapter.

Original Submission

upstart writes:

The web gains 13 million malicious new domains per month:

Akamai reckons that, in the first half of 2022 alone, it flagged nearly 79 million newly observed domains (NODs) as malicious.

According to the internet infrastructure giant, that amounts to 13 million malicious domain detections per month, equal to 20 percent of all successfully resolving NODs.

For Akamai's purposes, a NOD is any domain that has been queried for the very first time in the past 60 days. And by malicious, it means, a domain name that resolves to a destination that's intended to phish, spread or control malware, or cause some other online harm.

"[The NOD dataset] is where you find freshly registered domain names, typos, and domains that are only very rarely queried on a global scale," Akamai said. That list grows by approximately 12 million NODs per day, we're told, far more than a reasonable team of humans could hope to scan.

Akamai's methods of determining which domains are malicious or not are pretty straightforward. For one approach, it looks at a list of known domain generation algorithms (DGAs) that, with help credited to the greater cybersecurity community, Akamai was able to build into a 30-year predictive list it can use to identify DGA-registered domains.

DGA domains are often used by cybercriminals to share malware, host phishing pages, and the like, as they can be registered in bulk for even short-lived campaigns. The idea being that if you need a bunch of random-looking domain names from which to launch attacks, run botnet command-and-control servers, or host malicious pages, you don't want those domains to be easily guessed and blocked by, say, network security filters. So you have an algorithm that generates a deterministic series of domains, registers them, and your malware or phishing operation out in the wild can predict the domains they need to use at a given moment and connect to them.

[...] Akamai claims it only had a 0.00042 percent false positive rate among the 79 million malicious NODs it detected in the first half of the year.

Original Submission

upstart writes:

In the world's first operating system interview, Linux tells all about Windows, Torvalds, and its favorite distro:

Millions of people use Linux every day, but we rarely stop to think about how the operating system feels about it. Wouldn't it be nice to know what Linux really thinks about open source, Windows, Macs, and the command line? Until now, this has been impossible. But thanks to a new AI chat tool, we're able to find out.

Two weeks ago, a website called Character.AI opened a public beta that allows visitors to create a chat bot based on any character they can imagine. You input a few parameters, and the AI does the rest using a large language model similar to GPT-3. So we called forth "The Linux OS" as a bot to ask it a few questions about itself. The results were fun and surprising.

Using Character.AI is a lot like a texting conversation. You type in what you want to ask, and you read the AI character's responses in written form as the chat history scrolls upward. As with GPT-3, the code behind Character.AI has likely learned from absorbing millions of text sources found on the Internet. As such, its AI characters can easily respond with erroneous or fictional information. In fact, the site carries a bold disclaimer reading, "Remember: Everything Characters say is made up!"

[...] If you try it yourself—it's free at the moment during the beta—be aware that Character.AI's privacy policy states that the service may collect "the contents of any messages you send." The bots can be quite convincing.

upstart writes:

MIT Engineers Create Wireless, Battery-Free Underwater Camera - ExtremeTech:

As of now, a majority of the ocean has gone unprobed. Most of the underwater cameras used to investigate this part of the planet are incredibly unwieldy or expensive to operate: They either wire power from a separate vessel, thus limiting their mobility, or they require battery top-offs from crews on ships. Sending divers into hard-to-reach areas is typically a no-go, too, given the extreme amounts of pressure in places like the Mariana Trench and the deepest corners of the Gakkel ridge. Without the help of autonomous equipment, scientists are left to make educated guesses about what could be hidden in these mysterious places.

MIT's new camera could be exactly the equipment oceanographers and marine biologists need. The engineers started by creating an exterior containing transducers made of piezoelectric materials, or solids that produce electricity under certain mechanical stressors. As sound waves traveling through the water hit the camera, these piezoelectric transducers vibrate, converting mechanical energy into electrical energy. The camera can then use the energy or store it for later.

takyon writes:

NASA, SpaceX to Study Hubble Telescope Reboost Possibility

NASA and SpaceX signed an unfunded Space Act Agreement Thursday, Sept. 22, to study the feasibility of a SpaceX and Polaris Program idea to boost the agency's Hubble Space Telescope into a higher orbit with the Dragon spacecraft, at no cost to the government.

There are no plans for NASA to conduct or fund a servicing mission or compete this opportunity; the study is designed to help the agency understand the commercial possibilities.

SpaceX – in partnership with the Polaris Program – proposed this study to better understand the technical challenges associated with servicing missions. This study is non-exclusive, and other companies may propose similar studies with different rockets or spacecraft as their model.

NASA May Let Billionaire Astronaut and SpaceX Lift Hubble Telescope

During a news conference, Thomas Zurbuchen, NASA's associate administrator for science, said SpaceX had approached NASA several months ago with the idea. While he said the agency was willing to consider a proposal, he added that this was still a preliminary exploration. "I want to be absolutely clear," Dr. Zurbuchen said. "We're not making an announcement today that we definitely will go forward with a plan like this."

[...] After the fifth and last repair trip by NASA astronauts in 2009, the space shuttle Atlantis dropped Hubble off at an altitude of about 350 miles. In the 13 years since, the telescope has fallen by about 20 miles.

Hubble is not in immediate danger of falling out of the sky, but as it brushes against wisps of air, its orbit will continue to slowly and inexorably drop. By the end of the decade, the space telescope is likely to have dropped enough that NASA might have to make plans for how to guide its re-entry and destruction so that it would fall harmlessly into the ocean — unless someone could push it back up again.

Also at Teslarati, Ars Technica, and The Verge.

Original Submission

upstart writes:

It adds non-destructive editing, real-time effects, VST3 support and more:

Audacity is best known as a free app to do quick audio edits and record audio, but the latest update makes it more viable as a full on production tool, parent Muse Group has announced. Version 3.2 now supports non-destructive editing, real-time effects and enhanced VST3 support, along with user interface improvements and faster audio sharing via a new service, audio.com.

The most welcome addition is non-destructive audio capabilities that allow creators to adjust effects without the changes being permanently baked into the audio file. It also supports real-time playback of effects and crossfades as you adjust them, allowing for more accurate edits while listening to audio. That compares to previous versions, which required that you render the effect before you could hear it.

[...] Finally, the new audio.com site lets you easily share audio files by sending a link rather than the entire file. You can share files either publicly or privately, or use your account for cloud storage. (Muse Group recently updated its privacy policy, promising it wouldn't sell any of the "very limited" data it collects from users.) The new version of the app is now available as a free download.

Brief video showing the new features

Audacity is a great audio editing tool that is actually free. This update looks like it adds many more production level features.

Original Submission

upstart writes:

"We are screaming by pretty fast":

On Thursday morning, NASA's Juno spacecraft swooped down to within 358 km of the surface of Europa, the large, ice-encrusted Moon that orbits Jupiter.

This flyby will provide humanity its closest look at Europa since the Galileo mission made several close flybys more than two decades ago. However, the Juno spacecraft will carry a more powerful suite of instruments and a far more capable camera than Galileo. So this should be our best look yet at the intriguing world.

[...] Scientists have long been curious about Europa, which is covered in ice but believed to have a vast ocean beneath the surface due to the moon's warm core. There is probably more liquid water in Europa's global ocean than exists on Earth, planetary scientists think. While the ice sheet is believed to be several kilometers thick, the Hubble Space Telescope has collected data that indicates geysers may be periodically ejected through cracks in this ice. Given the presence of water and heat, this ocean is considered to be a potential reservoir for microbic alien life.

[...] The visual imagery and scientific data will help inform NASA scientists who are completing assembly of the Europa Clipper, a large spacecraft due to launch in 2024 on a Falcon Heavy rocket. This mission will be dedicated to the study of the Moon, arriving in 2030 and performing more than 50 flybys at close range to gather data. Eventually the space agency would like to send a lander but wants to obtain data from the flyby missions first to assess the best location for landing, potentially near a water vapor plume, if they really exist.

upstart writes:

How the CIA failed Iranian spies in its secret war with Tehran:

The spy was minutes from leaving Iran when he was nabbed.

Gholamreza Hosseini was at Imam Khomeini Airport in Tehran in late 2010, preparing for a flight to Bangkok. There, the Iranian industrial engineer would meet his Central Intelligence Agency handlers. But before he could pay his exit tax to leave the country, the airport ATM machine rejected his card as invalid. Moments later, a security officer asked to see Hosseini's passport before escorting him away.

Hosseini said he was brought to an empty VIP lounge and told to sit on a couch that had been turned to face a wall. Left alone for a dizzying few moments and not seeing any security cameras, Hosseini thrust his hand into his trouser pocket, fishing out a memory card full of state secrets that could now get him hanged. He shoved the card into his mouth, chewed it to pieces and swallowed.

Not long after, Ministry of Intelligence agents entered the room and the interrogation began, punctuated by beatings, Hosseini recounted. His denials and the destruction of the data were worthless; they seemed to know everything already. But how?

"These are things I never told anyone in the world," Hosseini told Reuters. As his mind raced, Hosseini even wondered whether the CIA itself had sold him out.

Rather than betrayal, Hosseini was the victim of CIA negligence, a year-long Reuters investigation into the agency's handling of its informants found. A faulty CIA covert communications system made it easy for Iranian intelligence to identify and capture him. Jailed for nearly a decade and speaking out for the first time, Hosseini said he never heard from the agency again, even after he was released in 2019.

upstart writes:

What Intel Learned When an Elevator Smashed Into Its Supercomputer Chips:

Intel has plenty of challenges in manufacturing processors. But it discovered a new one -- dangerous elevator doors -- during the development of Ponte Vecchio, the processor brains being used to construct the Aurora supercomputer.

Intel personnel were moving a bunch of the processors on a cart when a closing elevator door toppled it, Raja Koduri, leader of Intel's Accelerated Computing Systems and Graphics Group, said at Intel's Innovation conference Tuesday.

He didn't say how many were ruined, but the loss stung because they were initial samples used to test performance and look for problems. "Every one of them at that stage is expensive," Koduri said in an interview. With hundreds of manufacturing steps, it takes months to make a single advanced chip.

The elevator door wasn't just a one-off bummer. It actually revealed a problem that stood in the way of Intel's effort to reclaim its processor manufacturing leadership: human error.

Ponte Vecchio is a mammoth processor with more than 100 billion transistors, just about as many as anybody's processor in the business. To make something that big, Intel used its advanced packaging methods to bring together 47 separate slices of silicon.