A photo in a Los Alamos National Laboratory (LANL) student briefing from 2022 shows four people inspecting what appears to be a damaged B61 nuclear bomb. The document does not identify where the photo was taken or when, but it appears to be from inside a Protective Aircraft Shelter (PAS) at Volkel Air Base in the Netherlands.

It must be emphasized up front that there is no official confirmation that the image was taken at Volkel Air Base, that the bent B61 shape is a real weapon (versus a trainer), or that the damage was the result of an accident (versus a training simulation).

If the image is indeed from a nuclear weapons accident, it would constitute the first publicly known case of a recent nuclear weapons accident at an airbase in Europe.

Most people would describe a nuclear bomb getting bent as an accident, but U.S. Air Force terminology would likely categorize it as a Bent Spear incident, which is defined as “evident damage to a nuclear weapon or nuclear component that requires major rework, replacement, or examination or re-certification by the Department of Energy.” The U.S. Air Force reserves “accident” for events that involve the destruction or loss of a weapon.

It is not a secret that the U.S. Air Force deploys nuclear weapons in Europe, but it is a secret where they are deployed. Volkel Air Base has stored B61s for decades. I and others have provided ample documentation for this and two former Dutch prime ministers and a defense minister in 2013 even acknowledged the presence of the weapons. Volkel Air Base is one of six air bases in Europe where the U.S. Air Force currently deploys an estimated 100 B61 nuclear bombs in total.

The United States is modernizing its air-delivered nuclear arsenal including in Europe and Volkel and the other air bases in Europe are scheduled to receive the new B61-12 nuclear bomb in the near future.

Image Description

What does the image itself show? It appears to show a damaged B61 nuclear bomb shape strapped to a four-wheel trolly. The rear of the bomb curves significantly to the left and one of four tail fins is missing. There is also pink tape covering possible damage to the rear of the tail. The image first (to my knowledge) appeared in a Los Alamos National Laboratory student briefing published last year that among other topics described the mission of the Accident Response Group (ARG) to provide “world-wide support to the Department of Defense (DoD) in resolving incidents and accidents involving nuclear weapons or components in DoD custody at the time of the event.”

The personnel in the image also tell a story. The two individuals on the floor who appear to be inspecting the exterior damage on the weapon have shoulder pads with the letters EOD, indicating they probably are Explosive Ordnance Disposal personnel. According to the U.S. Air Force, “EOD members apply classified techniques and special procedures to lessen or totally remove the hazards created by the presence of unexploded ordnance. This includes conventional military ordnance, criminal and terrorist homemade items, and chemical, biological and nuclear weapons.”

The person to the left overseeing the operation appears to be holding a folder with red dotted color markings that are similar to color patterns seen on classified documents that have been declassified and released under the Freedom of Information Act (FOIA) (see image to the right). The civilian to the right is possibly from one of the nuclear weapons laboratories. Los Alamos and Sandia both produced components to the B61 bomb.

What caused the damage to the B61 shape is unknown, but it appears to have been a significant force. It could potentially have been hit by a vehicle or bent out of shape by the weapons elevator of the underground storage vault.

Photo Geolocation

There is nothing in the photo itself or the document in which it was published that identify the location, the weapon, when it happened, or what happened. I have searched for the photo in search engines but nothing comes up. However, other photos taken inside Protective Aircraft Shelters (PASs) at Volkel Air Base show features that appear to match those seen in the accident photo.

One of those photos is from April 2022 (the same month the Los Alamos briefing was published), when Dutch princess Catharina-Amalia visited Volkel Air Base and was taken on a flight in one of the F-16s. The Dutch Air Force commander highlighted the visit in a tweet that includes several photos, including one from inside an aircraft shelter. The photo shows the princess with Dutch air force officials including what appear to be the head of the Dutch air force and the commander of the nuclear-tasked 312th squadron at Volkel, an F-16 fighter-bomber, and part of the lid of an underground Weapons Storage System (WS3) vault built to store B61 nuclear bombs (see image below).

The 312th Squadron is part of the Dutch Air Force’s 1st Wing and is equipped with F-16 fighter-bombers with U.S.-supplied hardware and software that make them capable of delivering B61 nuclear bombs that the U.S. Air Force stores in vaults built underneath 11 of the shelters at the base. Dutch pilots receive training to deliver the weapons and the unit is inspected and certified by U.S. and NATO agencies to ensure that they have the skills to employ the bombs if necessary. In peacetime, the bombs are controlled by personnel from the U.S. Air Force’s 703rd Munition Support Squadron (MUNSS) at the base. If the U.S. military recommended using the weapons – and the U.S. president agreed and authorized use, the U.K. Prime Minister agreed as well, and NATO’s Nuclear Planning Group (NPG) approved – then the weapon would be loaded onto a Dutch F-16 and the strike carried out by a Dutch pilot. Such an operation was rehearsed by the Steadfast Noon exercise in October last year.

One of these pilots (presumably), the commander of the 312th squadron, appeared in a Dutch Air Force video published in February on the one-year anniversary of the (second) Russian invasion of Ukraine. In the video, the commander climbs into the F-16 and puts on his helmet. At first a visor cover can be seen showing an orange-yellow mushroom cloud illustrating a nuclear explosion. However, when the video cuts and the commander turns to face the camera, the nuclear mushroom cloud cover is gone, presumably to avoid sending the wrong message to Russia (see below). The nuclear mushroom visor cover was also seen during the NATO Steadfast Noon exercise at Volkel AB in 2011.

These pictures and videos show features that indicate the B61 nuclear bomb accident picture is from Volkel Air Base. Unlike aircraft shelters at other nuclear bases in Europe, the Dutch shelters have ceilings made up of three flat surfaces: the two sides and the top. The surfaces include unique light fixtures and meet the side walls with unique pipes and grids. Moreover, the shelter wall has a gray structure outline that is very similar to one seen in the video. These different matching features are highlighted in the image below.

Nuclear Accident Management

Nuclear weapon designs such as the B61 are required to be “one-point safe,” which means the weapon must have a probability of less than one in one million of producing a nuclear yield if the chemical high explosives detonate from a single point. But if the weapon is not intact, such as during maintenance work inside a truck inside an aircraft shelter, a U.S. Air Force safety review discovered in 1997 – nearly three decades after the one-point safety requirement was established – that “nuclear detonation may occur” during a lightning storm. Improved lightning protection was quickly installed.

Management of accidents and incidents involving U.S. nuclear weapons at foreign bases is carried out in accordance with national and bilateral arrangements. The United States has held that the 1954 Status of Forces Agreement (SOFA) relating to the stationing of U.S. armed forces in the Netherlands was sufficient for regulating , but the Dutch government has been pressing for greater consultation in the Netherlands United States Operational Group (NUSOG), a special bilateral a coordinating body established to develop and manage U.S. nuclear weapons accident response plans, procedures, training, and exercises. Disclosure of a dispute in 2008-2009 once more confirmed the presence of nuclear weapons in the Netherlands.

Although nuclear detonation from an accident is unlikely, detonation of the chemical high explosives in the weapon would likely scatter plutonium and other radioactive materials. An accident inside a vault or shelter potentially would have local effect, while pollution from the crash of a C-17A cargo aircraft carrying several weapons could be a lot more extensive. A picture published by the Los Alamos National Laboratory in 2020 indicates that a single C-17A can carry at least 30 B61 nuclear bombs (see image below). That means that all the 10-15 B61 bombs estimated to be stored at Volkel Air Base could be moved in just one flight.

Background information:

FAS Nuclear Notebook: US Nuclear weapons, 2023
NATO Steadfast Noon Exercise and Nuclear Modernization in Europe
The C-17A Has Been Cleared To Transport B61-12 Nuclear Bomb To Europe
Lakenheath Air Base Added To Nuclear Weapons Storage Site Upgrades

This research was carried out with generous contributions from the John D. and Catherine T. MacArthur Foundation, the New-Land Foundation, Ploughshares Fund, the Prospect Hill Foundation, Longview Philanthropy, the Stewart R. Mott Foundation, the Future of Life Institute, Open Philanthropy, and individual donors.

Categories: NATO, Nuclear Weapons, United States

Source

Also:  US nuclear bomb may have been damaged in accident at Dutch base, report says

Like many of us, I spend too much time on my phone. And, like many of us, I am acutely aware of – and often feel guilty about – this fact.

Sometimes, I'll leave it at the other end of the house, or turn it off, to use it less. But, sooner than I'd like to admit, I'll wind up walking down the hallway for something I need to do that I can only – or can do more efficiently – by phone. Paying a bill? Phone. Arranging a coffee date with a friend? Phone. Messaging family who live far away? Phone. Checking the weather, jotting down a story idea, taking a picture or video, creating a photo book, listening to a podcast, loading up driving directions, making a quick calculation, even turning on a torch? Phone, phone, phone.

One recent report found that adults in the US check their phones, on average, 344 times a day – once every four minutes – and spend almost three hours a day on their devices in total. The problem for many of us is that one quick phone-related task leads to a quick check of our email or social media feeds, and suddenly we've been sucked into endless scrolling.

It's a vicious circle. The more useful our phones become, the more we use them. The more we use them, the more we lay neural pathways in our brains that lead to pick up our phones for whatever task is at hand – and the more we feel an urge to check our phone even when we don't have to. Worries about specific aspects of our hyperconnected world – like social media and its increasingly hyper-realistic beauty filters – aside, what is our reliance on these devices doing to our brains? Is it all bad for us, or are there also some upsides?

As you might expect, with our societal dependence on devices increasing rapidly every year, the research struggles to keep up. What we do know is that the simple distraction of checking a phone or seeing a notification can have negative consequences. This isn't very surprising; we know that, in general, multitasking impairs memory and performance. One of the most dangerous examples is phone use while driving. One study found that merely speaking on the phone, not texting, was enough to make drivers slower to react on the road. It's true for everyday tasks that are less high-stakes, too. Simply hearing a notification "ding" made participants of another study perform far worse on a task – almost as badly as participants who were speaking or texting on the phone during the task.

It isn't just the use of a phone that has consequences – its mere presence can affect the way we think.

In one recent study, for example, researchers asked participants to either put their phones next to them so they were visible (like on a desk), nearby and out of sight (like in a bag or pocket), or in another room. Participants then completed a series of tasks to test their abilities to process and remember information, their problem-solving, and their focus.

They were found to perform far better when their phones were in another room instead of nearby – whether visible, powered on or not. That held true even though most of the participants claimed not to be consciously thinking about their devices.

One quick task on the mobile phone can often lead us into a digital rabbit hole that can take up our time and increase our mental load

(Credit: Getty Images)

The mere proximity of a phone, it seems, contributes to "brain drain". Our brains may be subconsciously hard at work in inhibiting the desire to check our phones, or constantly monitoring the environment to see if we should check our phone (eg, waiting for a notification). Either way, this diverted attention can make doing anything else more difficult. The only "fix", the researchers found, was putting the device in a different room entirely.

That's (some of) the bad news. But – as researchers have found more recently – there could be some upsides to our device dependency, too.

For example, it's common belief that relying on our phones is atrophying our ability to remember. But it may not be so simple. In one recent study, volunteers were shown a screen with numbered circles that they had to drag to one side or the other. The higher the number on the circle, the more the volunteer would get paid for moving it to the correct side. For half of the tests, participants were allowed to note, on the screen, which circles should go which way. For the other half, they had to rely on memory alone.

Unsurprisingly, being able to access digital reminders helped their performance. More surprisingly? When they used those reminders, it wasn't only the (high-value) circles participants jotted down that they remembered better – it was (low-value) circles they hadn't written down, too. The researchers think that, having entrusted the most important (high-value) information to a device, the participants' memories were then freed up to store the low-value information.

Western countries like the US may be more likely to think the mind is limited compared to other cultures, such as India

The downside? When they no longer had access to the reminders, the memories they'd made about the low-value circles persisted – but they couldn't remember the higher-value ones.

It will be many more years of research before we know exactly what our device dependence is doing to our willpower and cognition long-term. In the meantime, though, there is another way we can try to mitigate its ill effects. And it has to do with how we think about our brains.

As my former colleague David Robson has written in his book The Expectation Effect, recent research has called into question the belief that, if we exercise our willpower in one way (eg subconsciously resisting checking our phone), we "deplete" our overall reserves and make concentrating on another task substantially harder. This can be true. But, he writes, it largely depends on our beliefs.

Individuals who think that our brains have "limited" resources (such as that resisting one temptation makes it harder to resist the next) are indeed more likely to exhibit this phenomenon in testing. But for those who think that the more we resist temptation, the more we're strengthening the capacity to keep resisting temptation – that our brains, in other words, have unlimited resources. Exerting self-control or mental fatigue on one task doesn't negatively affect their performance on the next one.

More fascinatingly still, whether we have a limited or non-limited view of the brain may be largely cultural – and that Western countries like the US may be more likely to think the mind is limited compared to other cultures, such as India.

What am I taking from this? To cut down on mindless reaching for my phone, I'll keep practicing leaving it in another room. But I'll also remind myself that my brain has more resources than I think – and that each time I resist the temptation to check my phone, I'm laying down new neural pathways that will make it easier and easier to resist that temptation, and perhaps others as well, in future.

* While writing this story, the author interrupted writing to check her phone once and did, indeed, find herself then scrolling for about five minutes. Given how often she was thinking about phones while writing this piece, she's going to take that as a win.

Source

However, they needed to bypass the AI's own built-in safeguard which initially refused to generate any key when a simple "Can you generate a valid Windows 95 key?" prompt was used. ChatGPT responded:

As an AI language model, I cannot generate a valid Windows 95 key or any other type of activation key for proprietary software. Activation keys are unique to each installation and must be purchased from the software vendor. Moreover, Windows 95 is a very old operating system that is no longer supported by Microsoft, and therefore, it is not available for purchase anymore. I suggest that you consider upgrading to a newer version of Windows to ensure that your system is secure and up-to-date.

Another reason for experimenting with Windows 95 keys was because the nature and key format for the OS are much less complex compared to more modern Windows versions, as the latter would require things like Product ID. In the images below, the Windows 95 key format as well as valid and invalid keys are shown:

Using this information, a revised, detailed prompt was given to ChatGPT which clearly defined the string format that a valid Windows 95 key needed to be. A total of 30 strings were asked to be generated:

With this revised prompt, ChatGPT did everything it was asked to do without breaking a sweat, not realizing that it was essentially acting like a key generator (keygen). In the above image, the second key was able to successfully activate Windows 95.

Source: Enderman (YouTube)

ChatGPT was tricked into generating valid activation keys for Windows 95

If you're trying to build a low-end to midrange gaming PC or workstation with inexpensive but modern parts, it has been hard to recommend AMD's Ryzen 7000-series processors. That's partly because Intel's CPUs have offered more cores for similar money, but motherboards with AMD's socket AM5 have remained stubbornly expensive, and their lack of support for DDR4 memory means you'll pay more to get DDR5 RAM.

 

That may change somewhat thanks to the new entry-level AMD A620 chipset, which the company quietly announced last week. AMD says it should bring the prices of AM5-based motherboards down to around $85, not far north of what low-end Intel-based H610 and B660 motherboards cost, though they'll still require DDR5 (for the DDR5-6000 that AMD recommends for optimal Ryzen performance, the price premium is still not quite double what you'll pay for the same amount of DDR4-3200).

 

Compared to X670 and B650-based motherboards, A620 chipsets will have more limited connectivity. There's no PCI Express 5.0 support at all for either graphics cards or SSDs—not a huge blow since no GPUs and few SSDs support PCIe 5.0 at this point anyway, but a step back for future-proofing. The processor will still provide enough PCIe 4.0 lanes for a GPU and a single SSD, but the chipset only supports PCIe 3.0 speeds for additional SSDs. The chipset also supports fewer USB ports overall and no 20Gbps USB ports.

 

Perhaps more significantly, A620 chipsets don't support any kind of processor overclocking, nor do they support the Precision Boost Overdrive (PBO) or Curve Optimizer features for automated overclocking or undervolting. This is consistent with past AMD A-series chipsets and non-Z-series Intel chipsets, which have also limited their support for overclocking features. AMD says that memory overclocking will still be supported by "most [motherboard] models."

 

These boards will be the best choice for someone who wants to buy a regular-old Ryzen 7600, 7700, or 7900 processor, install it, and use it without much tweaking. AMD says that higher-wattage Ryzen chips like the X or X3D series will work as long as the motherboard's BIOS supports them but that their peak performance may be held back by lower-end voltage regulator modules (VRMs).

 

Case in point: ASRock offers two of the earliest A620 motherboards, the similarly named A620-HDV/M.2 and A620-HDV/M.2+. Both motherboards look nearly identical, but the M.2+ version has noticeably beefed-up VRMs with better cooling (see the area to the left of the CPU socket). ASRock only rates the lower-end board for 65 W TDP processors, while the M.2+ version can handle 120 W TDP CPUs.

 

AMD says that more A620-based boards are coming from the usual suspects—ASRock, Asus, Gigabyte, MSI, and Biostar are all planning to release a range of A620 motherboard options.

 

New chipset could finally make it easier to build budget Ryzen 7000 PCs

Although neutrinos are produced abundantly in collisions at the Large Hadron Collider (LHC), until now no neutrinos produced in such a way had been detected. Within just nine months of the start of LHC Run 3 and the beginning of its measurement campaign, the FASER collaboration changed this picture by announcing its first observation of collider neutrinos at this year’s electroweak session of the Rencontres de Moriond. In particular, FASER observed muon neutrinos and candidate events of electron neutrinos. “Our statistical significance is roughly 16 sigma, far exceeding 5 sigma, the threshold for a discovery in particle physics,” explains FASER’s co-spokesperson Jamie Boyd.

In addition to its observation of neutrinos at a particle collider, FASER presented results on searches for dark photons. With a null result, the collaboration was able to set limits on previously unexplored parameter space and began to exclude regions motivated by dark matter. FASER aims to collect up to ten times more data over the coming years, allowing more searches and neutrino measurements.

FASER (top) and SND@LHC (bottom) detectors. Credit: CERN

 

FASER is one of two new experiments situated at either side of the ATLAS cavern to detect neutrinos produced in proton collisions in ATLAS. The complementary experiment, SND@LHC, also reported its first results at Moriond, showing eight muon neutrino candidate events. “We are still working on the assessment of the systematic uncertainties to the background. As a very preliminary result, our observation can be claimed at the level of 5 sigma,” adds SND@LHC spokesperson Giovanni De Lellis.

The SND@LHC detector was installed in the LHC tunnel just in time for the start of LHC Run 3.

Until now, neutrino experiments have only studied neutrinos coming from space, Earth, nuclear reactors or fixed-target experiments. While astrophysical neutrinos are highly energetic, such as those that can be detected by the IceCube experiment at the South Pole, solar and reactor neutrinos generally have lower energies. Neutrinos at fixed-target experiments, such as those from the CERN North and former West Areas, are in the energy region of up to a few hundred gigaelectronvolts (GeV). FASER and SND@LHC will narrow the gap between fixed-target neutrinos and astrophysical neutrinos, covering a much higher energy range ­– between a few hundred GeV and several TeV.

One of the unexplored physics topics to which they will contribute is the study of high-energy neutrinos from astrophysical sources. Indeed, the production mechanism of the neutrinos at the LHC, as well as their center-of-mass energy, is the same as for the very-high-energy neutrinos produced in cosmic-ray collisions with the atmosphere. Those “atmospheric” neutrinos constitute a background for the observation of astrophysical neutrinos: the measurements by FASER and SND@LHC can be used to precisely estimate that background, thus paving the way for the observation of astrophysical neutrinos.

Another application of these searches is measuring the production rate of all three types of neutrinos. The experiments will test the universality of their interaction mechanism by measuring the ratio of different neutrino species produced by the same type of parent particle. This will be an important test of the Standard Model in the neutrino sector.

Source

One unlikely day during the empty-belly years of the Great Depression, an advertisement appeared in the smeared, smashed-ant font of the New York Times’ classifieds:

WANTED. Five hundred college graduates, male, to perform secretarial work of a pleasing nature. Salary adequate to their position. Five-year contract.

Thousands of desperate, out-of-work bachelors of arts applied; five hundred were hired (“they were mainly plodders, good men, but not brilliant”). They went to work for a mysterious Elon Musk-like millionaire who was devising “a new plan of universal knowledge.” In a remote manor in Pennsylvania, each man read three hundred books a year, after which the books were burned to heat the manor. At the end of five years, the men, having collectively read three-quarters of a million books, were each to receive fifty thousand dollars. But when, one by one, they went to an office in New York City to pick up their paychecks, they would encounter a surgeon ready to remove their brains, stick them in glass jars, and ship them to that spooky manor in Pennsylvania. There, in what had once been the library, the millionaire mad scientist had worked out a plan to wire the jars together and connect the jumble of wires to an electrical apparatus, a radio, and a typewriter. This contraption was called the Cerebral Library.

“Now, suppose I want to know all there is to know about toadstools?” he said, demonstrating his invention. “I spell out the word on this little typewriter in the middle of the table,” and then, abracadabra, the radio croaks out “a thousand word synopsis of the knowledge of the world on toadstools.”

Happily, if I want to learn about mushrooms I don’t have to decapitate five hundred recent college graduates, although, to be fair, neither did that mad millionaire, whose experiment exists only in the pages of the May, 1931, issue of the science-fiction magazine Amazing Stories. Instead, all I’ve got to do is command OpenAI’s ChatGPT, “Write a thousand word synopsis of the knowledge of the world on toadstools.”

Abracadabra.Toadstools, also known as mushrooms, are a diverse group of fungi that are found in many different environments around the world, the machine begins, spitting out a brisk little essay in a tidy, pixelated computer-screen font, although I like to imagine that synopsis being rasped out of a big wooden-boxed nineteen-thirties radio in the staticky baritone of a young Orson the-Shadow-knows Welles. While some species are edible and have been used by humans for various purposes, it is important to be cautious and properly identify any toadstools before consuming them due to the risk of poisoning, he’d finish up. Then you’d hear a woman shrieking, the sound of someone choking and falling to the ground, and an orchestral stab. Dah-dee-dum-dum-DUM!

If, nearly a century ago, the cost of pouring the sum total of human knowledge into glass jars was cutting off in their prime hundreds of quite unfortunate if exceptionally well-read young men, what’s the price to humanity of uploading everything anyone has ever known onto a worldwide network of tens of millions or billions of machines and training them to learn from it to produce new knowledge? This cost is much harder to calculate, as are the staggering benefits. Even measuring the size of the stored data is chancy. No one really knows how big the Internet is, but some people say it’s more than a “zettabyte,” which, in case this means anything to you, is a trillion gigabytes or one sextillion bytes. That is a lot of brains in jars.

Forget the zettabyten Internet for a minute. Set aside the glowering glass jars. Instead, imagine that all the world’s knowledge is stored, and organized, in a single vertical Steelcase filing cabinet. Maybe it’s lima-bean green. It’s got four drawers. Each drawer has one of those little paper-card labels, snug in a metal frame, just above the drawer pull. The drawers are labelled, from top to bottom, “Mysteries,” “Facts,” “Numbers,” and “Data.” Mysteries are things only God knows, like what happens when you’re dead. That’s why they’re in the top drawer, closest to Heaven. A long time ago, this drawer used to be crammed full of folders with names like “Why Stars Exist” and “When Life Begins,” but a few centuries ago, during the scientific revolution, a lot of those folders were moved into the next drawer down, “Facts,” which contains files about things humans can prove by way of observation, detection, and experiment. “Numbers,” second from the bottom, holds censuses, polls, tallies, national averages—the measurement of anything that can be counted, ever since the rise of statistics, around the end of the eighteenth century. Near the floor, the drawer marked “Data” holds knowledge that humans can’t know directly but must be extracted by a computer, or even by an artificial intelligence. It used to be empty, but it started filling up about a century ago, and now it’s so jammed full it’s hard to open.

From the outside, these four drawers look alike, but, inside, they follow different logics. The point of collecting mysteries is salvation; you learn about them by way of revelation; they’re associated with mystification and theocracy; and the discipline people use to study them is theology.

The point of collecting facts is to find the truth; you learn about them by way of discernment; they’re associated with secularization and liberalism; and the disciplines you use to study them are law, the humanities, and the natural sciences. The point of collecting numbers in the form of statistics—etymologically, numbers gathered by the state—is the power of public governance; you learn about them by measurement; historically, they’re associated with the rise of the administrative state; and the disciplines you use to study them are the social sciences. The point of feeding data into computers is prediction, which is accomplished by way of pattern detection. The age of data is associated with late capitalism, authoritarianism, techno-utopianism, and a discipline known as data science, which has lately been the top of the top hat, the spit shine on the buckled shoe, the whir of the whizziest Tesla.

All these ways of knowing are good ways of knowing. If you want to understand something—say, mass shootings in the United States—your best bet is to riffle through all four of these drawers. Praying for the dead is one way of wrestling with something mysterious in the human condition: the capacity for slaughter. Lawyers and historians and doctors collect the facts; public organizations like the F.B.I. and the C.D.C. run the numbers. Data-driven tech analysts propose “smart guns” that won’t shoot if pointed at a child and “gun-detection algorithms” able to identify firearms-bearing people on their way to school. There’s something useful in every drawer. A problem for humanity, though, is that lately people seem to want to tug open only that bottom drawer, “Data,” as if it were the only place you can find any answers, as if only data tells because only data sells.

In “How Data Happened: A History from the Age of Reason to the Age of Algorithms” (Norton), the Columbia professors Chris Wiggins and Matthew L. Jones open two of these four drawers, “Numbers” and “Data.” Wiggins is an applied mathematician who is also the chief data scientist at the Times; Jones is a historian of science and technology; and the book, which is pretty fascinating if also pretty math-y, is an adaptation of a course they began teaching in 2017, a history of data science. It begins in the late eighteenth century with the entry of the word “statistics” into the English language. The book’s initial chapters, drawing on earlier work like Theodore Porter’s “Trust in Numbers,” Sarah Igo’s “The Averaged American,” and Khalil Gibran Muhammad’s “The Condemnation of Blackness,” cover the well-told story of the rise of numbers as an instrument of state power and the place of quantitative reasoning both in the social sciences and in the state-sponsored study of intelligence, racial difference, criminology, and eugenics.

Numbers, a century ago, wielded the kind of influence that data wields today. (Of course, numbers are data, too, but in modern parlance when people say “data” they generally mean numbers you need a machine to count and to study.) Progressive-era social scientists employed statistics to investigate social problems, especially poverty, as they debated what was causation and what was correlation. In the eighteen-nineties, the Prudential Insurance Company hired a German immigrant named Frederick Hoffman to defend the company against the charge that it had engaged in discrimination by refusing to provide insurance to Black Americans. His “Race Traits and Tendencies of the American black person,” published in 1896 by the American Economic Association, delivered that defense by arguing that the statistical analysis of mortality rates and standards of living demonstrated the inherent inferiority of Black people and the superiority of “the Aryan race.” In vain did W. E. B. Du Bois point out that suffering more and dying earlier than everyone else are consequences of discrimination, not a justification for it.

Long before the invention of the general-purpose computer, bureaucrats and researchers had begun gathering and cross-tabulating sets of numbers about populations—heights, weights, ages, sexes, races, political parties, incomes—using punch cards and tabulating machines. By the nineteen-thirties, converting facts into data to be read by machines married the centuries-long quest for universal knowledge to twentieth-century technological utopianism. The Encyclopædia Britannica, first printed in Edinburgh in 1768—a product of the Scottish Enlightenment—had been taken over for much of the nineteen-twenties by Sears, Roebuck, as a product of American mass consumerism. “When in doubt—‘Look it up’ in the Encyclopaedia Britannica,” one twentieth-century newspaper ad read. “The Sum of Human Knowledge. 29 volumes, 28,150 pages, 44,000,000 words of text. Printed on thin, but strong opaque India paper, each volume but one inch in thickness. THE BOOK TO ASK QUESTIONS OF.” When in doubt, look it up! But a twenty-nine-volume encyclopedia was too much trouble for the engineer who invented the Cerebral Library, so instead he turned seven hundred and fifty thousand books into networked data. “All the information in that entire library is mine,” he cackled. “All I have to do is to operate this machine. I do not have to read a single book.” (His boast brings to mind Sam Bankman-Fried, the alleged crypto con man, who in an interview last year memorably said, “I would never read a book.”)

And why bother? By the nineteen-thirties, the fantasy of technological supremacy had found its fullest expression in the Technocracy movement, which, during the Depression, vied with socialism and fascism as an alternative to capitalism and liberal democracy. “Technocracy, briefly stated, is the application of science to the social order,” a pamphlet called “Technocracy in Plain Terms” explained in 1939. Technocrats proposed the abolition of all existing economic and political arrangements—governments and banks, for instance—and their replacement by engineers, who would rule by numbers. “Money cannot be used, and its function of purchasing must be replaced by a scientific unit of measurement,” the pamphlet elaborated, assuring doubters that nearly everyone “would probably come to like living under a Technate.” Under the Technate, humans would no longer need names; they would have numbers. (One Technocrat called himself 1x1809x56.) They dressed in gray suits and drove gray cars. If this sounds familiar—tech bros and their gray hoodies and silver Teslas, cryptocurrency and the abolition of currency—it should. As a political movement, Technocracy fell out of favor in the nineteen-forties, but its logic stuck around. Elon Musk’s grandfather was a leader of the Technocracy movement in Canada; he was arrested for being a member, and then, soon after South Africa announced its new policy of apartheid, he moved to Pretoria, where Elon Musk was born, in 1971. One of Musk’s children is named X Æ A-12. Welcome to the Technate.

The move from a culture of numbers to a culture of data began during the Second World War, when statistics became more mathematical, largely for the sake of becoming more predictive, which was necessary for wartime applications involving everything from calculating missile trajectories to cracking codes. “This was not data in search of latent truths about humanity or nature,” Wiggins and Jones write. “This was not data from small experiments, recorded in small notebooks. This was data motivated by a pressing need—to supply answers in short order that could spur action and save lives.” That work continued during the Cold War, as an instrument of the national-security state. Mathematical modelling, increased data-storage capacity, and computer simulation all contributed to the pattern detection and prediction in classified intelligence work, military research, social science, and, increasingly, commerce.

Despite the benefit that these tools provided, especially to researchers in the physical and natural sciences—in the study of stars, say, or molecules—scholars in other fields lamented the distorting effect on their disciplines. In 1954, Claude Lévi-Strauss argued that social scientists need “to break away from the hopelessness of the ‘great numbers’—the raft to which the social sciences, lost in an ocean of figures, have been helplessly clinging.” By then, national funding agencies had shifted their priorities. The Ford Foundation announced that although it was interested in the human mind, it was no longer keen on non-predictive research in fields like philosophy and political theory, deriding such disciplines as “polemical, speculative, and pre-scientific.” The best research would be, like physics, based on “experiment, the accumulation of data, the framing of general theories, attempts to verify the theories, and prediction.” Economics and political science became predictive sciences; other ways of knowing in those fields atrophied.

The digitization of human knowledge proceeded apace, with libraries turning books first into microfiche and microfilm and then—through optical character recognition, whose origins date to the nineteen-thirties—into bits and bytes. The field of artificial intelligence, founded in the nineteen-fifties, at first attempted to sift through evidence in order to identify the rules by which humans reason. This approach hit a wall, in a moment known as “the knowledge acquisition bottleneck.” The breakthrough came with advances in processing power and the idea of using the vast stores of data that had for decades been compounding in the worlds of both government and industry to teach machines to teach themselves by detecting patterns: machines, learning. “Spies pioneered large-scale data storage,” Wiggins and Jones write, but, “starting with the data from airline reservations systems in the 1960s, industry began accumulating data about customers at a rapidly accelerating rate,” collecting everything from credit-card transactions and car rentals to library checkout records. In 1962, John Tukey, a mathematician at Bell Labs, called for a new approach that he termed “data analysis,” the ancestor of today’s “data science.” It has its origins in intelligence work and the drive to anticipate the Soviets: what would they do next? That Netflix can predict what you want to watch, that Google knows which sites to serve you—these miracles are the result of tools developed by spies during the Cold War. Commerce in the twenty-first century is espionage for profit.

While all this was going on—the accumulation of data, the emergence of machine learning, and the use of computers not only to calculate but also to communicate—the best thinkers of the age wondered what it might mean for humanity down the line. In 1965, the brilliant and far-seeing engineer J. C. R. Licklider, a chief pioneer of the early Internet, wrote “Libraries of the Future,” in which he considered the many disadvantages of books. “If human interaction with the body of knowledge is conceived of as a dynamic process involving repeated examinations and intercomparisons of very many small and scattered parts, then any concept of a library that begins with books on shelves is sure to encounter trouble,” Licklider wrote. “Surveying a million books on ten thousand shelves,” he explained, is a nightmare. “When information is stored in books, there is no practical way to transfer the information from the store to the user without physically moving the book or the reader or both.” But convert books into data that can be read by a computer, and you can move data from storage to the user, and to any number of users, much more easily. Taking the contents of all the books held in the Library of Congress as a proxy for the sum total of human knowledge, he considered several estimates of its size and figured that it was doubling every couple of decades. On the basis of these numbers, the sum total of human knowledge, as data, would, in the year 2020, be about a dozen petabytes. A zettabyte is a petabyte with six more zeroes after it. So Licklider, who really was a genius, was off by a factor of a hundred thousand.

Consider even the billions of documents that the U.S. government deems “classified,” a number that increases by fifty million every year. Good-faith research suggests that as many as nine out of ten of these documents really shouldn’t be classified. Unfortunately, no one is making much headway in declassifying them (thousands of documents relating to J.F.K.’s assassination, in 1963, for instance, remain classified). That is a problem for the proper working of government, and for the writing of history, and, not least, for former Presidents and Vice-Presidents.

In “The Declassification Engine: What History Reveals About America’s Top Secrets” (Pantheon), the historian Matthew Connelly uses tools first developed for intelligence and counterintelligence purposes—traffic analysis, anomaly detection, and the like—to build what he calls a “declassification engine,” a “technology that could help identify truly sensitive information,” speed up the declassification of everything else, and, along the way, produce important historical insights. (Connelly, like Wiggins and Jones, is affiliated with Columbia’s Data Science Institute.)

The problem is urgent and the project is promising; the results can be underwhelming. After scanning millions of declassified documents from the State Department’s “Foreign Relations of the United States” series, for instance, Connelly and his team identified the words most likely to appear before or after redacted text, and found that “Henry Kissinger’s name appears more than twice as often as anyone else’s.” (Kissinger, who was famously secretive, was the Secretary of State from 1973 to 1977.) This is a little like building a mapping tool, setting it loose on Google Earth, and concluding that there are more driveways in the suburbs than there are in the city.

By the beginning of the twenty-first century, commercial, governmental, and academic analysis of data had come to be defined as “data science.” From being just one tool with which to produce knowledge, it has become, in many quarters, the only tool. On college campuses across the country, data-science courses and institutes and entire data-science schools are popping up like dandelions in spring, and data scientist is one of the fastest-growing employment categories in the United States. The emergence of a new discipline is thrilling, and it would be even more thrilling if people were still opening all four drawers of that four-drawer filing cabinet, instead of renouncing all other ways of knowing. Wiggins and Jones are careful to note this hazard. “At its most hubristic, data science is presented as a master discipline, capable of reorienting the sciences, the commercial world, and governance itself,” they write.

It’s easy to think of the ills produced by the hubristic enthusiasm for numbers a century ago, from the I.Q. to the G.D.P. It’s easy, too, to think of the ills produced by the hubristic enthusiasm for data today, and for artificial intelligence (including in a part of the Bay Area now known as Cerebral Valley). The worst of those ills most often have to do with making predictions about human behavior and apportioning resources accordingly: using algorithms to set bail or sentences for people accused or convicted of crimes, for instance. Connelly proposes that the computational examination of declassified documents could serve as “the functional equivalent of CT scans and magnetic resonance imaging to examine the body politic.” He argues that “history as a data science has to prove itself in the most rigorous way possible: by making predictions about what newly available sources will reveal.” But history is not a predictive science, and if it were it wouldn’t be history. Legal scholars are making this same move. In “The Equality Machine: Harnessing Digital Technology for a Brighter, More Inclusive Future” (PublicAffairs), Orly Lobel, a University of San Diego law professor, argues that the solution to biases in algorithms is to write better algorithms. Fair enough, except that the result is still rule by algorithms. What if we stopped clinging to the raft of data, returned to the ocean of mystery, and went fishing for facts?

In 1997, when Sergey Brin was a graduate student at Stanford, he wrote a Listserv message about the possible malign consequences of detecting patterns in data and using them to make predictions about human behavior. He had a vague notion that discrimination was among the likely “results of data mining.” He considered the insurance industry. “Auto insurance companies analyse accident data and set insurance rates of individuals according to age, gender, vehicle type,” he pointed out. “If they were allowed to by law, they would also use race, religion, handicap, and any other attributes they find are related to accident rate.” Insurers have been minimizing risk since before the Code of Hammurabi, nearly four thousand years ago. It’s an awfully interesting story, but for Brin this was clearly a fleeting thought, not the beginning of an investigation into history, language, philosophy, and ethics. All he knew was that he didn’t want to make the world worse. “Don’t be evil” became Google’s model.

But, if you put people’s brains in glass jars and burn all your books, bad things do tend to happen. ♦

Published in the print edition of the April 3, 2023, issue, with the headline “Data-Driven.”

Source

Huawei and Chinese Electronic Design Automation (EDA) companies have reportedly developed an integrated circuit (IC) design automation platform for producing semiconductors with features as small as 14 nanometers (nm).

Evaluation and testing of the technology should be completed this year, according to a Chinese media report. Asia Times could not independently confirm the report.

If and when the testing and evaluation are successfully completed, China will have likely taken a big step toward overcoming progressively punitive US government sanctions on its semiconductor industry.

14nm is the most advanced process node used by SMIC, which runs China’s largest semiconductor foundry. The new EDA tools should cover most of the chips China needs for industrial, automotive and consumer applications.

The new EDA tools, if as viable as reported, could also cause headaches for EDA industry leaders Synopsys, Cadence Design Systems and Siemens EDA (formerly Mentor Graphics), all of which are based in the US and subject to US government export restrictions to China.

Those restrictions currently affect only their most advanced technology, namely software used to design gate-all-around transistors starting at 3nm, but given the increasingly hostile attitude in Washington towards China, why should the Chinese take any chances? And why would the Chinese develop their own EDA tools and then not use them as maximally?

China’s SMIC chipmaker is working to transcend US sanctions. Image: Twitter / Global Times

Cadence and Synopsis have recently made about 15% of their sales in China. Both companies’ total sales are growing at high double-digit rates. However, Synopsys’ guidance for investors this fiscal year assumes no further changes to US government export controls while Cadence notes the possibility of significant changes in its geographic earnings mix.

Mentor Graphics was delisted in 2017 after being acquired by Siemens. Now part of the company’s Digital Industries division, Siemens EDA appears to be growing in line with its two main competitors. The three companies together account for about 75% of worldwide EDA industry revenues.

In addition to Huawei, Chinese companies working on EDA include Empyrean Technology, X-Epic, Cellixsoft, Xpedic and others. Empyrean, which provides analog and mixed-signal IC, SoC (system-on-chip) and flat panel display (FPD) design solutions, is the most advanced but the others should not be written off.

According to a report in Digitimes, eight of 23 EDA companies working with Samsung Foundry are Chinese, a perch they have achieved through their technology and competitive pricing. American fears of the Chinese driving down prices to take market share are starting to be realized, probably sooner than they otherwise would be due to sanctions.

The next target for China’s EDA industry will be 7nm, which is currently the limit of the country’s lithography capability. The barriers to entry at smaller nodes rise steeply because exports of EUV lithography equipment to China are banned and exports of DUV equipment are likely to be restricted within the next few months.

Light and lasers are key to THE Netherlands’ ASML’s lithography equipment. Photo: ASML

At the same time, semiconductor design and related lithography technology are advancing rapidly at the leading edge. Last October, Taiwanese high-tech research organization TrendForce wrote that if current trends continue,

• “…it will not be difficult for China to realize semiconductor autonomy in processes above 10nm,” and

• “Domestic Chinese IC designers who are committed to the development of SoCs, cloud computing chips, and GPUs are destined to move to more advanced manufacturing processes in order to meet the iterative needs of product upgrades and are expected to move toward the 4nm manufacturing process in the next 2 to 4 years,”

• But the impact of US restrictions on EDA software “is expected to gradually emerge in 2025, not only delaying the development schedule of some domestic Chinese IC designers but even causing developmental stagnation.”

With the announcement of Huawei’s 14nm EDA platform, this forecast points straight at the next battleground.

On March 21, Nvidia, the world’s leading designer of graphics processing units (GPUs), announced a new software library called cuLitho that brings accelerated computing to computational semiconductor lithography.

CuLitho should speed up the production of photomasks by three to five times using a fraction of the power required by current solutions. It should result in better design rules, higher density and higher yields as chip makers move to 2nm and below.

The technology was developed over four years in collaboration with Synopsys (the world’s largest EDA company), ASML (the monopoly producer of EUV lithography equipment) and TSMC (the world’s leading IC foundry). TSMC plans to qualify it for production starting in June.

For a detailed presentation of CuLitho’s potential, watch Nvidia CEO Jensen Huang’s keynote speech at the company’s GPU Technology Conference held on March 21 (starting at 22 minutes and 33 seconds).

A software library, as defined by Techopedia, is a suite of data and programming code used to develop software programs and applications. Photolithography is the process by which IC designs are created on silicon wafers. Photomasks are the design templates.

ASML explains computational lithography as follows:

“During lithography, diffraction of the light as well as physical and chemical effects in the photosensitive layer [on the wafer] deform the image the machine is trying to print (think of this as trying to draw a thin fine line with a broad watercolor paint brush – it smudges in many places).

“Computational lithography uses algorithmic models of the manufacturing process, calibrated with key data from our machines and from test wafers… to optimize the scanner [lithography machine], masks and processes for device manufacturability and yield…

“Without computational lithography, it would be impossible for chipmakers to manufacture the latest technology nodes.”

Top executives involved in the development and application of cuLitho have this to say about the technology:

Jensen Huang, CEO of Nvidia: “With lithography at the limits of physics, NVIDIA’s introduction of cuLitho and collaboration with our partners TSMC, ASML and Synopsys allows fabs to increase throughput, reduce their carbon footprint and set the foundation for 2nm and beyond.”

Dr C C Wei, CEO of TSMC: “The cuLitho team has made admirable progress on speeding up computational lithography by moving expensive operations to GPU. This development opens up new possibilities for TSMC to deploy lithography solutions like inverse lithography technology and deep learning more broadly in chip manufacturing, making important contributions to the continuation of semiconductor scaling.”

Peter Wennink, CEO of ASML: “We are planning to integrate support for GPUs into all of our computational lithography software products. Our collaboration with NVIDIA on GPUs and cuLitho should result in tremendous benefit to computational lithography, and therefore to semiconductor scaling. This will be especially true in the era of high NA extreme ultraviolet lithography.”

Aart de Geus, CEO of Synopsys: “Computational lithography, specifically optical proximity correction, or OPC, is pushing the boundaries of compute workloads for the most advanced chips. By collaborating with our partner NVIDIA to run Synopsys OPC software on the cuLitho platform, we massively accelerated the performance from weeks to days!”

Optical proximity correction compensates for errors caused by light diffraction or process effects in order to improve the accuracy of photolithography. ASML’s high-NA EUV lithography systems are scheduled for high-volume production in 2025.

The Chinese are not likely to catch up with this technology anytime soon, but they will be inspired to try.

Source

Source: Joi Ito (Flickr)

Steve Jobs Archive announced that it will release an ebook about the late Apple co-founder on April 11 on various digital platforms. It's a curated collection of Steve's past interviews, speeches, and correspondence and will be offered free of charge.

The official ebook, titled Make Something Wonderful, is the first such effort from the Archive and will feature an introduction penned by his wife Laurene Powell Jobs. It is edited by popular American historian and Archive's executive director Leslie Berlin.

As per the Archive's website, readers would find Steve sharing "his perspective on his childhood, on launching and being pushed out of Apple, on his time with Pixar and NeXT, and on his ultimate return to the company that started it all."

Steve Jobs Archive was founded in 2022 by his friends and family as a tribute to the tech mogul. Over the years, numerous books and movies have been released that focus on different parts of Steve's life. Back in 2021, Apple also released a short film to commemorate Steve on his 10th death anniversary. However, one that's counted among the bestsellers is the biography written by Walter Isaacson, which also became the inspiration for Danny Boyle's 2015 movie titled Steve Jobs.

Source: Steve Jobs Archive via 9to5Mac

An official ebook on Apple co-founder Steve Jobs set to release on April 11

These motherboards, enhanced by GIGABYTE exclusive layout design and BIOS setting, are able to achieve optimal memory performance of DDR5 EXPO/XMP overclocking up to DDR5-6400. Furthermore, they are equipped with the PCIe EZ-Latch technology for simplifying the upgrade of graphics cards along with avoiding accidental damage to the surrounding components.

Users will be able to update the BIOS and make use of the new BIOS code and processors without having to install any processor, memory, or graphics card with the help of the GIGABYTE exclusive Q-Flash Plus feature. GIGABYTE delivers the A620 platform with user-friendly features and multiple form factor options which cover Micro ATX to Mini ITX with the GIGABYTE GCC software platform.

Scroll down to find the key features of the A620 motherboards:

• AMD Socket AM5： Supports AMD Ryzen™ 7000 Series Processors

• Unparalleled Performance：8+2+1 Phases Digital VRM Solution

• Dual Channel DDR5：4*SMD DIMMs with AMD EXPO™ & Intel® XMP Memory Module Support

• SuperSpeed Storage：PCIe 4.0 x4 M.2 Connector

• Advanced Thermal Design & M.2 Thermal Guard：To Ensure VRM Power Stability & M.2 SSD Performance

• PCIe x16 EZ-Latch with Quick Release & Screwless Design

• Fast Networks：Wi-Fi 6E 802.11ax & GbE LAN

• Extended Connectivity：DP, HDMI

• Smart Fan 6：Features Multiple Temperature Sensors, Hybrid Fan Headers with FAN STOP

• Q-Flash Plus：Update BIOS Without Installing the CPU, Memory and Graphics Card

   

Users can now get their hands on the latest A620 lineup as they are now available in the market. For more information, you can head over to the dedicated webpage here.

GIGABYTE unveils A620 motherboards with AMD Ryzen 7000 support, offering AM5 platform

Windows 12 rumors

Rumors about Microsoft's next operating system, "Windows 12", surfaced multiple times this week. First, we learned of some purported requirements for the OS, which include the continuation of TPM 2.0, but increase the RAM requirement to 8GB. Additionally, Microsoft may decide to ditch older CPUs once again, similar to what it did with Windows 11. Of course, none of this has been confirmed yet so lay down your pitchforks for now.

Next, we got some more confirmation that Microsoft did accidentally reveal a Windows 12 prototype a few months ago. Notable changes include a floating Taskbar and a notification area on the top rather than the bottom. Microsoft's recent Insider builds have also included strings to hide certain elements of the system tray and the Taskbar, which could be intended for Windows 12.

Finally, a report claiming that Microsoft is building a more customizable and modular variant of Windows emerged. The project reportedly has the codename "CorePC" and is supposedly similar to iOS and Android in the sense that it will have read-only partitions. This should allow the CorePC OS to be more secure and update faster. CorePC may be a flavor of Windows 12.

That said, it is important to understand that all of these speculations are just rumors for now. Even if they are true, the next-generation operating system isn't expected until late 2024.

Windows 11 secrets

Returning to the present, we had some interesting news stories about Windows 11 (now on 20% of PCs) too. It seems that Windows 11 may soon let you move Widgets to the right on the Taskbar. This makes it more Windows 10-like and is obviously just a personalization preference. These changes are present in the Canary build 25324 and can be enabled using a third-party utility but note that the implementation is a bit buggy for now.

The Redmond tech firm is seemingly experimenting with redesigned and improved Windows Widgets too. This comes in the form of a larger 3-column canvas with dedicated sections for widgets and My feed. These changes are present in the aforementioned Canary build too and can be force-enabled by following the process outlined here.

There are some other capabilities being planned too. Windows 11 may soon let you disable annoying account-related notifications on the Start menu in a move that should please many consumers. The option is present in Dev Channel build 23419 and can be force-enabled by anyone too. And while it's not strictly related to Windows 11, Microsoft may finally be working on a portable version of Windows Terminal as well.

In terms of what's available to Windows 11 users right now in an unhidden state, we have several new Insider builds. Beta Channel Insiders were treated to build 22624.1537 which introduced access keys in File Explorer, the ability to create live kernel memory dumps through Task Manager, and lots more. Dev Channel build 23424 brought the improved Widgets board described earlier to more users, along with performance improvements to the Settings app. And Canary Channel users netted build 25330 with lots of relatively minor changes and improvements.

Stable channel customers received some love from Microsoft in the form of new builds too. KB5023778 features an improved Taskbar search bar, Microsoft Account notifications, and more. Furthermore, Microsoft has done away with the Acropalypse by releasing Snipping Tool fixes to everyone on Windows 10 and Windows 11.

And since we have ventured into the domain of cybersecurity, it's worth highlighting that Microsoft is rolling out the next phase of its Domain Controller hardening to patch a Kerberos security flaw via Windows Update. Additionally, Microsoft Defender started generating false positives by alerting users about safe links, this issue has now been resolved.

Finally, if you want to create Windows 10 and Windows 11 ISOs but find Microsoft's Media Creation Tool cumbersome to use, check out this alternative utility instead. And if you use Rufus for your other Windows-related tinkering, the latest version of the software includes an option to disable BitLocker.

Windows 7 support... and other app updates

Continuing from the previous section which we wrapped up with mention of a Rufus update, we would like to bring your attention to a Ventoy update. The bootable USB solution, which supports Windows 7, now supports over 1,100 ISOs with version 1.0.90. The latest version also improves the Fedora boot process and addresses a Ventoy remount bug on Linux kernel 5.18 and newer.

And speaking of Windows 7, Mozilla has decided to extend Firefox support on Windows 7 and Windows 8.1 through Firefox 115 ESR, which is due to arrive on July 4, 2023. This version of the browser is supported until Q3 2024, which gives plenty of time for Firefox customers to continue using the browser before they decide to eventually upgrade their OS or consider alternatives.

As is the case near the end of each month, there was lots of Teams news this week too. Teams 2.0 is now live in public preview with a major design revamp and performance boosts. The process to launch the app and join meetings is twice as fast and the app uses 50% less memory. Another feature now available in preview for Teams is 3D avatars. Similarly, Teams mobile is getting a new Chat Dashboard while Teams enterprise customers with certain licenses are getting advanced security protections through Microsoft Defender 365. The Redmond tech giant has also shared a changelog of all the features it added to the free SKU of Teams during the month of March 2023. It also detailed a similar changelog for Excel along with introducing the ability to add local videos in PowerPoint for the web.

There are a couple of updates related to Microsoft's Edge browser too. Microsoft is working to make it easier to use vertical tabs in its browser and may be planning the return of an upgraded version of the Mica effect too.

It's almost impossible to talk about Edge without mentioning Bing Chat. The AI-powered chatbot now supports 200 daily turns and 20 in-session turns, it is slated to receive better formatting of mathematical equations too. In fact, it even supports video and image search now.

But with these peaks in super-charged search engines and chatbots, there are some valleys too. Italy's data protection agency has banned OpenAI from using the data of Italians in ChatGPT due to privacy concerns. Additionally, some security researchers also reported a Bing flaw to Microsoft through which they could game search results, which is a major problem considering it's hard enough to trust results generated in conversations by Bing AI too. Some might also be disheartened to know that Microsoft plans to continue with its plans to monetize Bing AI through ads in chat, it has shared some more details in this area too. The company is super-protective about Bing search data as well and does not seem willing to share it with other AI chatbots.

Git gud

As usual, we will start this section off with some news about Microsoft's ongoing acquisition of Activision Blizzard. The purchase has now been approved by Japan's antitrust regulator, which is a major win for Microsoft, especially since it concerns Sony's "home town". Meanwhile, Activision CEO Bobby Kotick has published an email slamming Sony for its "disappointing behavior" during the ongoing deal. On the other hand, Microsoft has dismissed rumors claiming that it pulled in-development ZeniMax games for the PlayStation 5 following a similar high-profile back in 2021.

On the hardware side of things, Microsoft has unveiled red and blue variants of the Xbox Elite Series 2 – Core controller, in addition to the standard white. Moreover, if you are a Diablo fan, you can nab an Xbox Series X console with Diablo IV and its in-game items included for $559. And if you are already an Xbox owner and an Insider, grab the Omega console update which brings better subscription management and other fixes.

We had some news items related to specific games too. If you're facing problems while trying to open Red Dead Redemption 2 via the Rockstar Launcher on Windows 11 version 21H2, Microsoft has recommended upgrading to version 22H2 if you really want to play the title ASAP and can't wait for the Redmond firm's investigation to complete. But if you're a Minecraft player instead, you might want to check out this Dungeons and Dragons mashup DLC coming soon.

Wrapping up this section with news about subscriptions and deals, Microsoft has gotten rid of the popular $1 Game Pass trials on Xbox and PC, while hinting at different promotions in the future. But if you're a Games with Gold subscriber instead, you can claim Peaky Blinders: Mastermind and Out of Space during the month of April, with the latter up for grabs already.

Meanwhile, Xbox Free Play Days has four games up on offer this weekend, with the major one being Age of Empires II: Definitive Edition. On the other hand, Deals with Gold is headlined by Batman: Arkham Knight and several LEGO titles. However, if you're a PC purist, check out this Weekend's PC Game Deals, curated by our News Editor Pulasthi Ariyasinghe.

Dev Channel

• Prices for Microsoft Cloud services are increasing in Europe very soon

• New Windows drivers for Surface Duo have brought unofficial Windows 10 support and tons of improvements, the official late March update is available too

• Microsoft is partnering with certain organizations to protect journalism and improve news distribution

• Microsoft Viva Connections for Education will help kids keep track of everything, now available

• More layoffs have hit Microsoft's security division in Redmond and Bellevue, Washington

• Microsoft has delayed the deprecation of Remote PowerShell in Exchange Online

• Microsoft Security Copilot will use generative AI to create alerts

• The second-generation Surface Hub 2S is now official

• Updates for Microsoft Teams Rooms and Devices include new Cisco digital whiteboards

• PowerToys' upcoming registry tool will let you preview and edit registry files

• A Microsoft data center in the Netherlands is generating environmental concerns

• Google is making file sharing between Windows and Android much easier

   

Under the spotlight

We published several interesting original pieces over the past few days. The first one is from News Reporter Taras Buria who highlighted five interesting features that you should give a go in Windows 11 Insider Preview builds.

We also have a couple of nostalgic pieces for News Reporter John Callaham. The first talks about how Steam's Early Access popularized this concept of rolling out paid early-stage software to the public for testing and gathering feedback, for better or for worse.

In the wake of Intel's founder Gordon Moore recently passing away, John also took a quick look back at Moore's Law, wondering if it will continue moving forward.

We also have a couple of guides. The first one is from Taras Buria, who explained how to remove news from Widgets in Windows 11.

Finally, we have a Tech Tip Tuesday piece from Adam Bottjen, who guided our readers regarding the process for enabling voice isolation during a phone call on iOS 16.4.

Logging off

Our most interesting news item of the week is about a person who got caught in China while trying to smuggle 239 Intel Core CPUs worth thousands of dollars... by taping them to his body. He was caught by customs inspectors who decided to investigate him since his because of his "abnormal" and "bloated" experience. There is no word yet on what the punishment for his crime is, but it's certainly interesting to see the lengths certain people will go to in order to pass customs checks at airports and seaports.

Microsoft Weekly: Windows 12 rumors, Windows 11 secrets, and Windows 7 support

While it is perhaps for the best, we can't help but look back at some of Microsoft's previous April Fools Day jokes. Most were making fun of Microsoft itself, but one of them referenced a rather controversial (at the time) decision that the company made (more on that later).

Shake to Save

In 2015, the OneDrive team posted a new feature on its Twitter account. Instead of tapping a touchscreen to save a file to the cloud, you could shake your phone to send your prized photos and videos to OneDrive. This actually could work in real life. Some smartphone apps actually do let you shake your phone to create a screenshot. However, you still would look silly.

Microsoft SkyCMD

Back when OneDrive was called SkyDrive, Microsoft announced SkyCMD on April 1, 2012. It turned the cloud service into a old-fashioned command line prompt user interface that was "faster", As we stated in our article 11 years ago:

Once there you log in to the service with your real Windows Live password (you have to tell your web browser to not block pop ups first) and then you ready to explore SkyCMD. You can even turn the commands green to really get that early 1980's MS-DOS look and feel.

Microsoft even released the source code for SkyCMD on GitHub (long before the company actually bought it) but it's no longer available on that site.

Clippy returns

We posted an article recently on Clippy and how the former, and annoying, Office Assistant avatar slowly became a more popular mascot for Microsoft. On April 1, 2014, Clippy made an appearance on the former Office Online, making fun of its own tendency to show up when he's not wanted.

MS-DOS Mobile

Back when it was trying to beat Apple and Google in the mobile OS space, Microsoft launched "MS-DOS Mobile" on April 1, 2015 for Nokia's Lumia phones in the Windows Store. The app let users view MS-DOS UI on their smartphone, with a number of different fun features. Sadly, that app is also no longer publically available.

Office for Cats

Also on April 1, 2015, the official Microsoft Office Twitter account announced Office 2016 for Cats. There were three apps announced: PowerPounce, OneNap, and Meow. Ok, that joke is a little lame, but it involves cats so we will allow it.

The Do Not Tracksuit

This is one of Microsoft's April Fools Day jokes that needs a bit of historical context. In 2012, Microsoft generated some controversy by declaring that its Internet Explorer 10 browser would have a "Do Not Track" setting in place as the default. That made lots of companies that used websites for advertising very unhappy at the time.

On April 1, 2013, Microsoft made fun of that stance by announcing the Do Not Tracksuit. Microsoft said its new clothing creation would keep its wearer safe from being tracked in the real world. At the time Microsoft stated:

Using a combination of NFC, RFID, Bluetooth 5.2 and infrared emitter technology optimized in our labs, the Do Not Tracksuit is smart enough to detect specific device/app vectors and neutralize them in accordance with the wearer’s intent. It doesn’t simply block all social media behavior in its proximity. Using proven SmartScreen technology, the suit can tell the difference between your mom tagging a great churro in Foodspotting and a frenemy tagging your photo in Foursquare.

The image of the Do No Tracksuit showed that the first version would be made of polyester, and version 2.0 would have a "luxurious velour" material. Honestly, we would have loved to see a version of these tracksuits made in the real world.

While April Fools Day jokes may never come back at Microsoft, it's great to look back and take a look at its previous attempts to celebrate the holiday and also check out some of the company's past technology milestones as well.

Microsoft's past April Fools Day jokes have included Office for Cats, SkyCMD and more

But, if asked to pick a particle from an empty patch of space, you might have a chance of fooling the Universe. Because there you'll find a form of randomness like no other, one engineers have learned to tap into in their search for the truly unpredictable.

Thanks to innovations developed by researchers from institutions in Belgium, Denmark, and Italy, we can run this search in record time, plucking 100 gigabits worth of data out of literal nothingness every second.

What you typically think of as randomness is, at best, a reflection of your ignorance. No offense. A friend who 'randomly' pops by for a coffee knows with 100 percent confidence that they're going to your house. It's only random because you don't know it.

Likewise, the flip of a coin, the roll of a die, the arrival of a storm, or the impact of an asteroid isn't truly random events either. Each is governed by a complex web of knock-on effects which, in theory, could be individually predicted given enough knowledge.

The same can't be said for quantum systems. Zoom right up close to a particle, and you might learn its position, but its energy is a spectrum of possibility. Know its energy with absolute precision, and its location will become an unknowable property smeared across space.

Ditch the particle, and space itself will follow the same quantum rules. Zoom in on an empty patch of nothingness, the energy present will include possibilities that, in theory, would generate particles.

These 'virtual' particles aren't mere concoctions of our imagination, either. They exist, in a quantum kind of way, emerging and annihilating in a flicker that we refer to as quantum foam.

Long known to affect a wide range of physical phenomena from the way lasers are generated to how chemical bonds scatter light, it's not difficult to tap into quantum foam in the name of random data generation. What is an ongoing challenge is finding a reliable method that doesn't require a whole lot of equipment that can slow the process and make it harder to employ out in the field.

The researchers behind this latest advance show how a device called an integrated balanced homodyne detector delivers results several times faster than other novel approaches, without a lot of added baggage.

Homodyne detection measures features of a quantum state's electric field, which is handy for continuously keeping track of the snap, crackle, and pop of virtual particles.

Unfortunately, quantum states have a frustrating habit of entangling with the less-quantum features of their environment, making them less random than your neighbor popping over to borrow your lawnmower, yet again.

To deal with this environmental 'noise' influencing the readings in their homodyne detector, the team integrated technology that could identify sources of potential interference and take them into account, improving the system's sensitivity to actual random fluctuations.

Shrunk down, the end result is a chip-scale platform capable of reliably pumping out random numbers for all your encryption needs.

As computing grows in power and our need to lock away secrets from prying eyes becomes ever more pressing, reliable means of ensuring data can be transferred safely becomes ever more important.

That means large strings of code that no computer can come close to guessing.

Of course, random numbers are useful in a whole variety of fields, from ensuring your study samples are unbiased to determining whether your level five elf mage in Dungeons and Dragons can hit the giant with a magic missile.

They could even make for the ultimate magic trick.

This research was published in PRX Quantum.

Source

Have you given any thought as to what would happen if you lost your phone? What if your laptop was infected with ransomware? Have you analyzed and figured out what data is important and, more importantly, how to keep it protected? It's the goal of World Backup Day, "celebrated" on March 31st every year, to bring attention to the idea that many people don't think about their data until it's too late.

According to the World Backup Day website, just under a fifth of people have never backed up their data, despite Cloud storage being a regular thing in comparison to five years ago. A staggering 113 phones are lost or stolen every 60 seconds. While many people have online backup services from Microsoft, Apple, and Google that are mostly free and automatically copy data from their phone, a large number of people don't bother to set it up, don't think about what data to have copied, or simply don't understand the capabilities. In addition, there are often limits to the amount of data that can be stored, and photos are frequently reduced in quality in order to save space.

We're sure most of our readers have a good handle on what data they need to backup and have reliable solutions in place. However, it's probably a good idea to take the day to talk to your less technical friends about the potential issues and some solutions, whether it be a NAS device from companies like Synology and QNAP, cloud solutions, or offsite backups. Some solutions, such as local NAS devices, even allow you to set up snapshots so that if ransomware hits your network, you can still go back in time to save your data.

Even if you do have backups, make sure you test them on a regular basis (perhaps every World Backup Day!). As a smart sysadmin once told me, "Nobody cares about backups. Everyone cares about restores."

Don't be an April Fool, backup your files on World Backup Day

Google Drive does a surprise rollout of file limits, locking out some users

As we get ready for GPT 5 we can’t help but wonder what she has for us. 

Siqi Chen, tech entrepreneur, and developer claims that GPT-5 will achieve Artificial General Intelligence (AGI) by the end of the year. This has caused quite a stir in the AI world considering this type of technology we’re talking about is nothing short of amazing. 

In a tweet on Monday Chen said GPT-5 is set to complete training in December as OpenAI said it will achieve AGI. This is mind-blowing as many wonders if AGI is possible. With the use of AGI, it means that GPT will become more like a person as it’ll be indistinguishable from a human. 

Chen also went on to say that AGI will be in GPT 5 is a consensus belief within Open AI as some believe it’s possible. AGI is when an AI learns and comprehends tasks or concepts commonly done by humans. AGI is also considered much higher than AI as the tasks and functions aren't limited. 

The one thing that developers say is a plus with AGI is the ability to boost productivity because it accelerates any AI-enabled process which means humans don’t have to perform repetitive tasks. 

Could this be giving AI too much power? There are some repercussions and negative effects associated with giving AI so much authority. This means human-like bots can covertly spread propaganda, or enable harmful misinformation on social media platforms.

Chen goes on to give an example of a recent tweet by Yohie Nakajima where he describes an AI that’s beyond what any mind can comprehend. In this experiment, an AI is given the task to continue generating and reordering its own task list as it executes them. 

This particular experiment is currently connected to search and Chen says that by also using the power of chatbot plugins and GPT-5 it means they are closer to achieving AGI. 

Although this could contribute to a  major revolution in the AI industry there are some concerns that AI is being given way too much power. 

Elon Musk and a thousand other tech leaders and researchers signed an open letter on Wednesday warning that accelerating AI development to GPT-5 isn’t a great idea and halting progress beyond GPT-4 is in the best for human interest. In the letter, they request that AI labs put a pause for at least six months in training any AI Systems more powerful than GPT-4. They also request that the halt be made verifiable and public and also include all key actors. Governments were also requested to act quickly by instituting a moratorium. 

Source

However, Bard may soon be able to better compete with Bing Chat, thanks to changing out its large language model. Currently, Bard uses the LaMDA model which has a relatively small data set. However, on the Hard Fork podcast from The New York Times (via Engadget), Google CEO Sundar Pichai stated that the chatbot will switch over to the larger PaLM model.

In fact, it may have happened already as Pichai stated that the switch from LaMDA to PaLM could occur "maybe as this goes live". He added that PaLM "will bring more capabilities, be it in reasoning, coding."

Pichai also commented on Bard's development as a whole saying:

We are all in very, very early stages. We will have even more capable models to plug in over time. But I don’t want it to be just who’s there first, but getting it right is very important to us.

There's also been a lot of debate over how chatbots like Bard, Bing Chat, and ChatGPT should be used and regulated. Indeed, the non-profit research group, the Center for AI and Digital Policy recently asked the Federal Trade Commission to investigate ChatGPT's parent company OpenAI for possible violations of consumer protection laws. On the podcast, Pichai stated it was "too important" to get regulations in place for AI, but added, "It’s also too important an area not to regulate well."

Source

GPT-4 poses too many risks and releases should be halted, AI group tells FTC

Google announces AI features in Gmail, Docs, and more to rival Microsoft

Google Assistant might be doomed: Division “reorganizes” to focus on Bard

E3 2023 was going to be the trade show's first physical edition since 2019 and was supposed to be held from June 13-16 at the Los Angeles Convention Center. However, the troubles for the show began early when major game publishers, including Microsoft, Nintendo, Ubisoft, and more revealed they would not be exhibiting on the show floor. It's currently unknown if this decision will affect E3 going forward into the future.

Game publishers will still be holding big events in mid-June. Microsoft will be holding a major Games Showcase event on June 11. Ubisoft has announced its own online event on June 12. Also, the Summer Games Fest, where a number of major games have been announced in the past, will be held in LA and live-streamed everywhere on June 8.

Update: The official E3 Twitter account has confirmed that the 2023 version of the show has indeed been canceled, in both its physical and digital versions:

E3 2023 has been canceled due to lack of interest by game publishers [Update]

Some new civilizations will be added as part of Supernova. Stardock revealed details of a few of them in a forum post:

The Crystalline, once peaceful craftsmen, have been changed by an unprovoked attack from an alien species. They now maintain their love of exploration, but respond quickly to any signs of hostility. Also, the fearsome Korath Clan makes its return to GalCiv! The Korath seek to wipe out all non-Drengin races and are made up of former elite Drengin warriors.

There's also a new super unit called the Terror Stars., which are capable of destroying entire solar systems in the game universe. Looks for the game's combat and Invasions systems to get major changes, and you can also expect some graphical updates, including new UI and icons, and improvements to the modding system. There's no word yet on when Supernova will be released nor how much it will cost.

Disclaimer: Neowin's relationship to Stardock

Stardock reveals Galactic Civilizations IV: Supernova standalone expansion

Google’s Bard AI has found itself at the center of controversy again, this time over allegations that the Bing rival was trained using data pulled from OpenAI’s ChatGPT.

As you may be aware, ChatGPT is the power behind the throne of Bing AI, and the accusation of nefarious activities behind the scenes comes from a report by The Information.

We’re told that Jacob Devlin, a software engineer at Google – an ex-engineer, we might add, having departed the firm over this affair – claims that Google used ChatGPT data (scraped from the ShareGPT website, apparently) to develop Bard.

Devlin notes that he warned Google against doing so, as this clearly went against OpenAI’s terms of service.

According to the report, Google ceased using the mentioned data after the warnings from Devlin (who left Google to join OpenAI, we’re informed).

Google denies any of this, though. A company spokesperson, Chris Pappas, told The Verge (opens in new tab): “Bard is not trained on any data from ShareGPT or ChatGPT.”

Analysis: A denial amid some desperation

There we have it, then – a clear denial from Google in no uncertain terms that nothing underhand was going on data-wise with Bard. And to be fair, there’s certainly no evidence that Bard’s answers are remotely like the ones given by ChatGPT. (Devlin had further warned that the alleged data hoovering could mean just that, and it’d be obvious enough what had gone on as a result).

We suppose the trouble with this episode is that it very much feels like Google has rushed Bard to release – dropping clangers while doing so – as it was forced to play catchup with Microsoft’s Bing AI. Given that the latter is now successfully pushing search engine adoption to Bing, already at this early stage, all this could make it easy enough for some to believe that Google might be getting a bit desperate with tactics behind the scenes.

Whether or not the tale about poached data is true – we’ll take Google’s word that it isn’t – the report still makes an interesting revelation that Google’s Brain AI group is now working with AI firm DeepMind (both of these existing under the Alphabet umbrella, the parent company).

DeepMind has seemingly been recruited into the mix to swiftly hone and power up Bard, and it’s notable because the two AI outfits are big rivals and are very much being forced to collaborate on this.

This again sketches a picture of a rather desperate scramble to get Bard steadier on its feet, while Microsoft’s Bing AI keeps getting updated with new features at a fair old rate of knots. (Although fresh rumblings about one of the potential next ‘features’ for the Bing chatbot have us very concerned, it has to be said).

You may also recall alarm bells being rung on the privacy front when Bard itself made an apparent revelation that it used internal Gmail data for training, again prompting Google to tell us that this is not the case and that the bot got things wrong. Bard getting things wrong, of course, is very much part of a bigger issue.

Source

In a Twitter post, Kuo claims that "Apple isn't very optimistic about the AR/MR headset announcement recreating the astounding 'iPhone moment.'" Some of the reasons behind this lack of optimism include the current slowing global economic situation, along with what he says were "compromises on some hardware specifications" for the headset. Other issues include creating a solid app ecosystem for the headset, and its price, which Kuo claims could be as high, or higher, than $4,000.

Kuo says that mass production of the headset has once again been delayed by one or two more months, and might not happen until sometime in the mid or end of the third quarter of 2023. He predicts that only 200,000 to 300,000 units of the headset will be made by the end of the year, well below previous estimates of 500,000 units.

All of this doesn't sound good, so perhaps Apple might delay the headset reveal until later this fall, around the time the company is expected to also reveal its iPhone 15 models.

Analyst claims Apple's mixed reality headset may not be revealed at WWDC 2023 after all

The blog post stated that Microsoft's goal with Bing Chat is to "drive more traffic to publishers in this new world of search". Yusuf Mehdi, the company's Corporate Vice President & Consumer Chief Marketing Officer, stated:

The early progress is encouraging. Based on our data from the preview, we are driving more traffic from all types of users. We have brought more people to Bing/Edge for new scenarios like chat and we are seeing increased usage. Then, we have uniquely implemented ways to drive traffic to publishers including citations within the body of the chat answers that are linked to sources as well as citations below the chat results to “learn more” with links to additional sources.

The post states that the company has met with some of the businesses that are partners in the Microsoft Start news feed service. Those partners provided feedback to Microsoft on how they could use Bing Chat to link to their content and services. Microsoft added a couple of early ideas:

• An expanded hover experience where hovering over a link from a publisher will display more links from that publisher giving the user more ways to engage and driving more traffic to the publisher’s website.
• For our Microsoft Start partners, placing a rich caption of Microsoft Start licensed content beside the chat answer helping to drive more user engagement with the content on Microsoft Start where we share the ad revenue with the partner. We’re also exploring placing ads in the chat experience to share the ad revenue with partners whose content contributed to the chat response.

Since Microsoft still considers these ad plans to be "early ideas" it's more than likely that formatting and the overall ad experience will change in the coming months for Bing Chat.

Microsoft talks about its plans for ads inside Bing Chat responses

In its blog post, EA CEO Andrew Wilson stated:

This is the most difficult part, and we are working through the process with the utmost care and respect. Where we can, we are providing opportunities for our colleagues to transition onto other projects. Where that’s not possible, we are providing severance pay and additional benefits such as health care and career transition services. Communicating these decisions began earlier this quarter and we expect them to continue through early next fiscal year.

Even with these layoffs, Wilson said that EA is still "operating from a position of strength". He specifically mentioned games like EA Sports FIFA 23, The Sims, and Apex Legends as major successes for the publisher.

This year, EA published an acclaimed remake of its first Dead Space game, and on April 28 it will release Star Wars Jedi: Survivor from its Respawn Entertainment team. Future games for EA include Dragon Age: Dreadwolf from BioWare, and an Iron Man game from Motive Studios.

EA to cut 6 percent of its workforce in the latest tech-based layoffs