Security teams log 54% of successful attacks and alert on just 14%. The rest move through your environment unseen.
The Picus whitepaper shows how breach and attack simulation tests your SIEM and EDR rules so threats stop slipping by detection.

Adam Savage has spent years turning movie props into objects he can actually touch and use. His earlier work on Rounders chips and a matching poker table showed how deeply he loves the gear that surrounds a serious game. This new project takes that same passion and points it at his favorite Bond film. Casino Royale features one of the most intense poker scenes ever put on screen, complete with million-dollar plaques and sky-high tension. Savage decided to build the kind of custom carrier and racks that might actually move such a set between games.
He began by looking for realistic copies rather than making things from scratch, as the details might be very confusing. One manufacturer, Apache Poker Chips, sent him several ceramic pieces that mimic the chips depicted in the movie in every aspect, including weight, sound when knocked together, and feel in your hand. To top it all off, the set includes these large plaques that are worth a million dollars each, as they have the same styling and design as the high-roller tables in Montenegro. It all adds up to over 65 million dollars, but that’s still nowhere near the ultimate sum from the film.
Sale
Next came the design process, which involved Savage working with his shop assistant to create specialized racks that could carry many more chips than a regular tray. Each rack has 175 chips, organized into five stacks of 35. They produced the racks on a two-color machine, so the Casino Royale emblem is visible through the plastic as part of the design. With six racks in all, the set has plenty of capacity, but it all fits in one large case with a lock. Getting it just right required some careful computer work and a lot of test printing to ensure that the fit and logo were correct.

The plaques needed some boxes to keep them in, so Savage used the table saw to make some wooden trays, angled the cuts so the boxes would stack nicely and stand out when pulled out with those old drawer handles. After some testing, he decided to producing them using a 3D printer, which allowed him to get a smoother finish that looked like it belonged in a fine shop. Each box may hold a number of plaques and has the same two-color design treatment as the chip racks.

The case, however, is the true standout, as Savage started with a massive anvil-style box that was essentially a strongbox and then transformed it into something that resembles a bank vault on wheels. He fitted boat-style latches and a very good lock on each side. There are plastic bits to assist everything line up when you seal the lid, and the inside of the lid has a small tufted trim for a luxurious feel. He polished it off with some old aircraft stickers, a Montenegrin flag, and some tamper-evident seals, making it look like something from an extremely secretive high-stakes operation.

The problem is that once the case is filled, moving it around becomes difficult because it weighs around 19kg on its own, before you even consider the box itself. So Savage decided to link the box to one of those stainless steel moving kitchen carts, allowing one person to move it without exerting themselves. Inside the cart, he also fitted some custom 3D-printed card carriers that look just like the original mid-century designs, ensuring that you always have two decks of cards ready. The entire operation is now sitting on the cart, and every detail has been meticulously planned. The chips sound and feel just like the ones in the movie, and the plaques are also spot-on.
7-Zip version 26.02 was released to fix a remote code execution vulnerability that could allow attackers to execute malicious code by convincing users to open specially crafted compressed files.
The vulnerability, disclosed by Lunbun researcher Landon Peng, exists in 7-Zip’s processing of XZ-compressed data.
According to an advisory from the Zero Day Initiative, specially crafted XZ data can trigger a heap-based buffer overflow, potentially allowing attackers to execute arbitrary code as the user.
While the developer has not published technical details about the flaw, the changes in the 26.02 source code suggest it is related to how 7-Zip tracks available space while decompressing XZ data.
The patch adds checks to ensure the decoder cannot write beyond the remaining available space in an output buffer, helping prevent a heap-based buffer overflow.
The advisory states that exploitation requires user interaction, such as visiting a malicious page or opening a malicious archive file.
As 7-Zip does not include an automatic update feature, users will not receive the security fix automatically. Instead, they must install it manually by downloading the latest version from the program’s official site, 7-zip.org.
Because 7-Zip is one of the most widely used archive utilities on Windows, security flaws impacting its archive features are an attractive target to threat actors.
A phishing campaign or social engineering attack could be used to distribute a malicious archive that exploits the flaw to install malware on vulnerable systems.
This is not far-fetched, as archive vulnerabilities, including those in 7-Zip, have been exploited in past attacks.
In early 2025, a 7-Zip vulnerability that allowed malware to bypass Windows’ Mark of the Web (MotW) security feature was exploited by Russian hackers as a zero-day.
Later that same year, a Russian hacking group exploited a WinRAR vulnerability tracked as CVE-2025-8088 via phishing attacks to install the RomCom malware.
There are currently no reports that attackers are actively exploiting this newly disclosed 7-Zip vulnerability.
However, users are advised to update to version 26.02 as soon as possible to reduce the risk of future attacks.
Security teams log 54% of successful attacks and alert on just 14%. The rest move through your environment unseen.
The Picus whitepaper shows how breach and attack simulation tests your SIEM and EDR rules so threats stop slipping by detection.
There are many smartwatches that are water-resistant, but rarely is anything fully waterproof. That said, you can safely swim (in freshwater sources) with one that meets an IPX8, IP68 (or higher) rating. But there’s still risk of damage if the watch isn’t dried out after submersion, which is why features like the Apple Watch’s water lock are really handy. With water lock activated, the Apple Watch not only disables the screen so pressure from water doesn’t inadvertently trigger an unintended action, but it also ejects water from inside the device to help it dry faster.
It’s a useful and underrated feature of Apple Watch that every smartwatch should have, especially those that are rated to be safe to wear while swimming. I use this feature often with my Apple Watch Series 11, and I love that it’s automatically triggered any time I hop in a pool or wade in the ocean. It works while scuba diving as well if you have the Apple Watch Ultra, Apple Watch Ultra 2 or Apple Watch Ultra 3, all three of which are safe for deep diving (standard Apple Watches are not).
To manually turn on water lock, which is available on all Apple Watch models from Series 2 and onward, press the side button to open the Control Center. Select the water droplet icon (you may have to scroll down to see it). When the water lock is active, you won’t be able to manipulate the watch screen. It simply won’t respond. Once you come out of the water, press and hold the Digital Crown to unlock the watch. You will see a water ejection mode begin and hear a series of tones, which sound sort of like an ’80s video game, until the process is done.
What’s happening inside the watch when you do this? It’s pretty fascinating. When you press and hold the button, water comes streaming out of the tiny side speaker holes. It’s a lot more water than you might realize or even notice, since it happens so fast and the speakers and water droplets are so tiny. The watch pauses to settle and eject again, repeating this cycle over and over. This is why you have to press and hold the Crown for at least a few seconds instead of a quick press. It keeps you from initiating this process accidentally.
When should you use water lock? It’s a no-brainer to use the water lock feature on Apple Watch if you’re a swimmer or have a pool at home. In fact, you won’t have a choice, since it turns on automatically when you’re engaged in a water exercise like swimming or surfing. As an extra precaution, you might want to turn it on manually using the steps noted above during times when your wrist isn’t completely submerged, but the watch still gets wet. This might be if you wear it in the shower, while washing dishes or just during a run home in the rain. Utilizing this feature will ensure that any residual water is removed.
What happens if you don’t turn on water lock? The watch will likely be fine (assuming it’s a model with a high water-resistance rating), but you run the risk of water pooling inside and causing eventual damage. While that water-resistance rating gives you the confidence to wear an Apple Watch while swimming or doing other water-based activities, you should be aware that water-resistance weakens over time with any device. Keeping as much water out of the insides as possible, especially if you’re swimming in a chlorinated pool, can help prolong the life of your smartwatch. Next time you go for a swim, see if you can spot the water coming out of the side speaker when you press the button. And consider the intricate process that’s happening to keep the watch free of moisture inside.

A coalition of activists and community organizations plans to rally Sunday outside Anduril’s Seattle office, protesting the defense technology company’s development of artificial intelligence-powered military systems and its growing presence in the region.
The demonstration, scheduled for 9:30 a.m. at Anduril’s downtown Seattle office, is being organized by groups including BAYAN Washington, International Coalition for Human Rights in the Philippines and The International League of Peoples’ Struggle. Organizers say the event will highlight concerns about the use of AI in warfare, autonomous weapons systems and the expansion of defense technology companies in Washington state. They expect more than 50 to attend.
“The rally will respond to urgent developments in the expansion of AI weapons companies in Washington State and will expose Anduril as an engine of U.S.-led wars of aggression and a domestic threat to migrant and working class communities,” the organizations said in a statement.
Anduril said it recognizes the right to protest, while defending its work supporting the U.S. military and service members.
“We respect the right to free speech and we understand that protests are a hallmark of democratic expression,” Anduril said in a statement provided to GeekWire. “That said, it is perplexing when people choose to protest a company dedicated to supporting the very military that safeguards those rights.”
The company’s statement continued:
“At Anduril, we’re proud of our role in helping the brave men and women who risk their lives to defend the freedoms that we all enjoy, freedoms that include the right to stand outside and protest our existence. We’ll continue to honor those serving our country, even when others stand in opposition.”
The protest comes as Anduril expands its operations in the Seattle area, including a new maritime manufacturing and testing operation along Seattle’s historic Lake Washington Ship Canal. GeekWire reported earlier this year that the company has taken over the former Foss shipyard, where it is thought to be testing autonomous vessels for the U.S. Navy.
Founded in 2017 by entrepreneur Palmer Luckey, Anduril has become one of the most prominent defense technology companies in the country, developing autonomous aircraft, maritime systems, surveillance technologies and AI-powered software platforms for military and national security customers.
@media (max-width: 600px) {
aside.callout { float:none !important; max-width:100% !important; margin-left:0 !important; margin-right:0 !important; }
aside.callout .callout-img { display:none !important; }
}
The company’s Seattle expansion has drawn attention because of the region’s long history as a hub for aerospace, maritime engineering, artificial intelligence and advanced manufacturing. The new maritime facility on the south bank of the Ship Canal represents a new chapter for a site with deep roots in Seattle’s shipbuilding history.
In announcing the rally, organizers cited the company’s work on autonomous systems, including underwater and surface vessels, and raised concerns about the role of artificial intelligence in global conflicts.
The groups also pointed to the ongoing Rim of the Pacific (RIMPAC) military exercises, a multinational naval exercise held in and around Hawaii. The exercise runs through July 31 and includes participation from dozens of nations.
Anduril has increasingly positioned itself as a technology company focused on modernizing defense capabilities, arguing that faster adoption of advanced software, autonomy and AI can improve the effectiveness and safety of military operations.
Sunday’s event is expected to include speeches, testimonials and cultural performances from participating community organizations.
The rally adds a new point of public debate around Anduril’s expansion in Seattle, as the company builds out its presence in a region already home to major technology companies, aerospace firms and a growing defense innovation sector.
In addition to the new facility at the Foss shipyard, Anduril operates facilities in downtown Seattle and Bellevue, where it expanded last summer with a lease for 39,851 square feet of space at Skyline Tower.
Anduril also is rapidly expanding its operations in California, where the company is headquartered. And it is building a massive facility just south of Columbus, Ohio, that it dubs Arsenal-1, described by the company as “the future of American defense manufacturing.”
In May, the company raised a $5 billion funding round from Thrive Capital, Andreessen Horowitz and others at a $61 billion valuation.
Looking for a different day?
A new NYT Strands puzzle appears at midnight each day for your time zone – which means that some people are always playing ‘today’s game’ while others are playing ‘yesterday’s’. If you’re looking for Saturday’s puzzle instead then click here: NYT Strands hints and answers for Saturday, July 18 (game #867).
Strands is the NYT’s latest word game after the likes of Wordle, Spelling Bee and Connections – and it’s great fun. It can be difficult, though, so read on for my Strands hints.
Want more word-based fun? Then check out my NYT Connections today and Quordle today pages for hints and answers for those games, and Marc’s Wordle today page for the original viral word game.
SPOILER WARNING: Information about NYT Strands today is below, so don’t read on if you don’t want to know the answers.
• Today’s NYT Strands theme is… Big talk
Play any of these words to unlock the in-game hints system.
• Spangram has 11 letters
• First side: left, 8th row
• Last side: right, 8th row
Right, the answers are below, so DO NOT SCROLL ANY FURTHER IF YOU DON’T WANT TO SEE THEM.
The answers to today’s Strands, game #868, are…
The letter Z helped me get the spangram — eventually, as I got “size” first, then “supersize” before finally SUPERSIZEIT.
Even though I understood the theme immediately and had an idea of the words we were searching for, I really struggled to put them together .
Although rarely used, LEVIATHAN is an incredible word (it features in the Bible, describing a fire-breathing sea serpent).
I was thinking that it really should be the name of a horror or at least a wrestler when a Google search told me that both already exist; the 1989 horror flick made less cultural impact than Dave Batista, who used the nickname Leviathan before becoming The Animal. Every day’s a school day with Strands.
Strands is the NYT’s not-so-new-any-more word game, following Wordle and Connections. It’s now a fully fledged member of the NYT’s games stable that has been running for a year and which can be played on the NYT Games site on desktop or mobile.
I’ve got a full guide to how to play NYT Strands, complete with tips for solving it, so check that out if you’re struggling to beat it each day.
UK sales of Chinese-made cars hit 285,000 in 2025, up from 384 in 2015. No additional tariff on plug-in hybrids makes the UK more open than the EU or US.
Brits bought 384 Chinese-made vehicles in 2015. Last year, they bought 285,000, according to automotive consulting firm Mobility Global. The growth is accelerating. BYD nearly doubled its UK sales in the first half of 2026 to over 37,000 units, and Chinese brands collectively hold roughly 13% of new car registrations in Britain, double their share a year ago.
The reason is a tariff gap. The EU charges countervailing duties of up to 35.3% on Chinese battery-electric vehicles and is preparing additional tariffs on plug-in hybrids. The US charges 100%. The UK charges neither. Britain applies no additional tariff on Chinese plug-in hybrid vehicles, which has made it the easiest major Western market for Chinese automakers to enter at scale. “It becomes an excellent size market that’s progressing well towards electrification and is in demand for some cheaper vehicles with that void to fill,” said Will Roberts of Benchmark, an automotive consultancy.
The price gap is stark. A Volkswagen Tiguan plug-in hybrid built in Germany sells in the UK for just over £43,000 ($58,000). The BYD Seal U built in China costs almost £10,000 less. Buyers at a Geely dealership in Maidstone told CNBC the value proposition was obvious: better equipment, lower price. Canada opened its market to Chinese EVs in January with a 49,000-unit cap, but the UK’s approach is more permissive, with no quota and no additional duties.
China’s domestic auto market is cooling. Retail sales fell 26% in the first half of 2026 while exports rose 72%, according to the China Association of Automobile Manufacturers. That export surge has to go somewhere. Former GM board member Jon McNeill told CNBC that Chinese automakers are entering Europe “with really attractive cars at really attractive prices with technology that sort of blows away what they can buy from a European manufacturer.” Geely has already stopped building new factories and is using Volvo’s existing plants instead to sidestep tariffs and absorb overcapacity. The UK’s open door may not last: if Chinese market share keeps climbing, pressure to align with EU tariff policy will follow. For now, 285,000 cars in a single year tells its own story.
Waymo says robotaxi service has resumed after it made “temporary adjustments” in San Francisco amidst a power outage that appears to have affected around 7,000 PG&E customers in the city.
According to a screenshot posted on social media, Waymo told SF customers that service was “temporarily paused” and that “freeway routes are unavailable.”
When TechCrunch reached out to the Alphabet-owned company for comment, a spokesperson said in a statement, “We are making temporary adjustments to our service while we monitor local conditions. We know riders depend on us, and we will return to normal operations as soon as possible.”
Following the initial publication of this article, a Waymo spokesperson added that the company “decided to pause service for approx. one hour to assess the scale of the power outage affecting a large portion of San Francisco and coordinate with local officials.”
Power outages have affected Waymo service in the past, for example when a number of Waymo vehicles stalled on city streets during a blackout in December, and when a similar incident paralyzed traffic during a Golden Gate Bridge fireworks show on the Fourth of July.
As a result, San Francisco Mayor Daniel Lurie has called for tougher state regulations to “adequately address how autonomous vehicles operate during major incidents, planned or not.”
This post has been updated with additional comment from Waymo reflecting that service has resumed.
France’s regulatory authority for licensed gambling/betting games “announced this week that it ordered ISPs to block access to Polymarket,” reports Engadget. Anyone caught advertising an unauthorized betting site “could be fined up to 100,000 euros, or around $114,000.” (The article notes this follows a previous regulatory action from November placing a geoblock on financial transactions from French residents on Polymarket’s site.)
In May Spain blocked access to Polymarket and Kalshi while it launched a gambling license investigation.
Unlike most cutting lasers, femtosecond lasers don’t vaporize materials; rather, they produce such short, intense bursts of light that the affected region is ablated without having the chance to heat its surroundings. This makes them good at cutting away material without damaging the surroundings, something [Ben Krasnow] exploited to cut cross-sections of samples while still in a scanning-electron microscope.
In this case, the samples were crickets, and before imaging they had to be prepared. First, the bodies were soaked in glutaraldehyde to cross-link the proteins and stabilize the structure. Next, a series of solvent exchanges replaced the water in the bodies with a low-surface-tension solvent; this meant that during the next step, drying, surface tension wouldn’t distort the crickets’ internal structure. Finally, the insect bodies were charred under argon, which made the bodies conductive and more absorptive to laser light.
The laser itself and the scanning galvo are mounted outside the microscope, and shine in through a transparent window. To protect the detector and electron optics from a spray of ablated carbon, a servo motor swings an aluminium shutter between these and the sample while the laser is active. This caused some mysterious problems during testing: after the first ablation run, the electron microscope’s image would contain so much noise as to be unusable, but it would improve over time. As it turned out, the shutter was painted, and the other side of the paint was getting coated with charged carbon particles. This created a small capacitor which disrupted the electron optics as it discharged. Eventually, after solving this and a few other strange problems, [Ben] was able to take several time-lapse videos of the laser gradually ablating a cricket, 30 microns at a time, revealing its inner structure.
Although scanning-electron microscopes are unfortunately shard to come by, it’s still possible to restore a secondhand microscope or, as [Ben] did, build your own. Femtosecond lasers are yet more inaccessible, though they can be used to replicate themselves.
AI chatbots are everywhere these days, and they seem to “know” about everything. But while that is a strength, it can sometimes be a weakness because it isn’t laser-focused on one topic. Not so with this Ham-radio-centric chatbot called HamGPT. The service is clearly built on another GPT engine but understands how to retrieve data from common ham radio sources, such as the FCC database, propagation reports, and the like. It didn’t, however, seem to have access to ham radio-related books, magazine articles, or other “static” data that we could tell.
You do have to sign up for an account, which includes providing your callsign and location. There is a free tier that allows a limited number of queries per day, so you can try it to see if it is useful for you without subscribing.
Here’s a typical session:
What band will have the best propagation to Japan from my QTH right now?
The best band for Japan from your QTH right now is 30 meters, which shows good propagation reliability. 20 meters is also active and providing a viable path.
Real-time data confirms activity on both bands, primarily using FT8. While the path is open, the signals are relatively weak (typical for this long-haul path), making digital modes like FT8 or CW your best bet for a successful contact.
Would you like me to check if your current antenna setup is suitable for these bands, or perhaps help you calculate dimensions for a 30m or 20m antenna?
In addition, bubbles at the bottom of the screen showed me the busiest band in my area and how many repeaters were nearby.
In all fairness, we asked ChatGPT the same question, but did say “ham radio band” just to give it some idea of scope. It gave a much more detailed answer with sources, even provided headings, and made a suggestion about another location I sometimes operate from because it remembers things from previous unrelated chats.
We understand reactions will be mixed. If you’ve been a ham for a long time, you probably could have guessed that a path from the US to Japan in the morning was likely to be on 20 or 30 meters. You probably also know how to look things up yourself.
We didn’t try any more sophisticated queries that might make it more worthwhile. For example, what if you could send it an ADIF log file and ask it what awards you qualified for? Or to process contest logs for duplicates and fill out a scoring worksheet? What would you like a ham radio-aware AI to do for you?
Ham radio — at least parts of it — has become inextricably linked with computers.
This week Slashdot reader joshuark found the story of exactly how in 2025 ProPublica reporter Renee Dudley confirmed Microsoft was running tech support for the U.S. Defense Department through China, America’s biggest cybersecurity adversary — and how that investigation ultimately changed U.S. government policy.
The reporter first found an ad offering $18 to $28 to hire Americans as “digital escorts” for China-based tech support, then just searched LinkedIn for people who apparently had answered the ad. They discovered that at the time “Behind the scenes, unseen by the users at the U.S. government, it’s not just one person who responds,” explains ProPublica’s podcast. “It’s two people… The China-based engineer is the one who knows how to fix the problem. On their end, they produce a block of code to solve it and send it over to the digital escort in the U.S. The digital escort then just copy-pastes it… All of this so that they can follow the government’s rule: that you have to be a U.S. citizen or permanent resident to handle sensitive data.”
But amazingly to confirm it, ProPublica’s researcher just had to input “Microsoft” and “escort” into the U.S. Patent Office search bar, and actually found patents related to digital escorts — along with names of the current and former Microsoft employees listed as inventors. Had the government signed off on the practice? “I could see what Microsoft actually told the government,” the reporter says on the podcast, “And there was no mention of foreign engineers being used, and definitely no mention of China.”
ProPublic’s story was published on a Tuesday, according to the podcast, and by Friday “Microsoft said it had stopped using China-based engineers to support Defense Department cloud systems.” And America’s Defense Department “also opened up an investigation, looking into whether any of Microsoft’s China-based engineers had compromised the government’s national security.
London Mayor Sadiq Khan handed a peerage by Keir Starmer alongside 15 other Labour figures… just days before the PM leaves No10
Weekend Open Thread – Corporette.com
The House | The City of London can help the new chancellor deliver growth in every postcode
CFTC blocks Kalshi from unwinding Michigan trades after court order
Young campaigners urge incoming PM to act on outdoor junk food ads
Nvidia Stock Slips After Big Tuesday Rally as Huang Confirms Vera Rubin Chip Is Now in Production Today
Ripple Payments Joins MiCA With 14 Firms, Does It Mean Anything For XRP?
Disney’s Most Ambitious Failed Star Wars Attraction Is Coming to SDCC
Ripple wins EU-wide access as ESMA adds it to MiCA register
Palantir Shares Rise After Expanded Nvidia Partnership and Fresh Analyst Upgrades Ahead of Earnings Day
Injective Submits SEC Transfer-Agent Registration to Onchain Ownership Records
Get Your ESP32 Sunny Side Up With This Solar Dev Board
XRP BOMBSHELL… XRP OMBOARDED FOR TRANSACTIONS!!!
Dark Secrets Emerge When Jailbreaking LLMs
Registration is now open for March for Men with Kev 2026
New Cornerback Enters Vikings Trade Rumor Mill
Money | Class 12 Economics | CBSE Board Exam 2026-27
Banco Bilbao Vizcaya Argentaria, S.A. (BBVA) Discusses Global Macro Environment and Economic Outlook for Core Markets Transcript
Claude Fable 5 Slips to Second in AI Coding Leaderboard
Cloudflare Precursor Watches Your Mouse and Keyboard To Decide If You Are Human
You must be logged in to post a comment Login