Valve is a darling among PC gamers. Steam as a platform is beloved, the Steam Deck created the handheld gaming PC boom. But there’s a darker side of the company, especially when it comes to game monetization. The state of New York says that the way Valve sells loot boxes in games like Counter-Strike is illegal gambling. And the state wants to prove it in court. Attorney General Letitia James brought the suit (PDF link) against the PC gaming giant yesterday, alleging that Valve has created a market for randomized virtual items that operates as an illegal casino, including secondary markets that give those items tangible, real value, and that they pose an especially potent threat to children. The 47-page filing lays out the company’s history of digital distribution, its network of digital item sales and how they can be traded and even converted into real currency, and how it allegedly designed the process of opening loot boxes to operate “similar to the spin of a slot machine.” New York claims that 96 percent of Counter-Strike digital items are effectively worth less than the keys purchased to randomly unlock them, making the entire process a digital casino. To demonstrate, it offers up “case openings” on YouTube, where the real-world value of items is displayed as streamers scream in glee. One linked from the filing has 1.5 million views, and a sponsor link to an affiliate site where loot boxes can be bought and sold with regular digital payments. In laying out how the virtual video game items have real-world, tangible value, the suit says that “Valve designed and built its games and the Steam platform to enable users to sell the virtual items they have won.” Players can trade items through Steam directly via the community market or on third-party sites that organize player-to-player trades, often facilitating cash transfers. Built-in Steam tools, like the Trade URL, allow for easy integration on third-party services. “Unlike the Steam Community Market, which caps transaction amounts,” New York argues, “third-party sites enable users to sell rare virtual items from Counter-Strike, Team Fortress 2, and Dota 2 for tens of thousands of dollars.” This is manifestly true, as high-value Counter-Strike skin sales frequently make headlines. The market for Counter-Strike skins alone is estimated to be worth multiple billions of dollars, even though selling virtual items for real cash is a violation of the Steam user agreement. New York alleges that Valve has selectively enforced these rules, prosecuting the most blatant “skin casinos” while allowing cash sales to go unchallenged. The lawsuit includes this screenshot from a streamer unlocking a Counter-Strike skin with a real-world value on screen. State of New York Steam itself does not allow for transfers of actual cash…but Steam Wallet credit, which can be purchased with real money and used to buy games or hardware like the Steam Deck, is pretty darn close. As the suit says, “These funds have the equivalent purchasing power on the Steam platform as cash.” New York argues that since players can use this credit to buy games, which do have set values, Steam store credit operates the same as actual currency for the purposes of gambling. It even gives an example of an investigator who sold a Counter-Strike knife skin, bought a Steam Deck handheld with the store credit, and then sold the Steam Deck in a store (presumably a pawn shop or game store) to buy other electronics. New York argues that through ready availability and deliberate gambling mechanics, Valve’s games offer the same risks and perceived rewards as casino gambling, facilitating gambling addiction in the same way. This is especially true for children and teens, the suit says, and “teenagers and children compromise a significant segment of Valve’s users.” The state hopes to “permanently enjoin” Valve from violating New York law, make restitution to consumers, and “disgorge all monies resulting from the illegal practices,” and pay a fine of three times the amount it earned from the allegedly illegal practices. Equating loot box and gacha game design with gambling has been a hot-button issue for years, though actual prosecution has been rare. Because the items won are virtual and, at least technically, have no direct monetary value, most games get away with it. Austria, the Netherlands, and Belgium have especially harsh laws and interpretations of existing laws that view loot boxes and similar mechanics and gambling, while some countries restrict them from being sold to minors. Various state bills and one national bill in the United States intended to ban or otherwise regulate loot box sales, but none have actually been passed. The suit makes a strong and convincing opening statement. But even in a relatively liberal state, the New York Attorney General has her work cut out for her. Attempted civil and criminal prosecutions of video game monetization have generally been very difficult, and Steam (and, indeed, Counter-Strike skins) basically prints money for Valve. An army of spawn-camping lawyers could spend years finding ways to define just about anything Valve does as, if not totally legal, then probably not explicitly illegal. Read...

The top Democrat on the congressional panel investigating Epstein has called on the attorney general to publish the material. Read...

The viral OpenClaw AI tool has already spawned dozens of imitators on GitHub and has spurred pivots from major AI players like Meta. Now Perplexity is throwing its hat into the personal AI agent arena, with a new tool that can put teams of sub-agents under your command. Unveiled on Wednesday, Computer is being billed as a “general-purpose digital worker that operates the same interfaces you do”–or, as chief Perplexity business officer Dmitry Shevelenko calls it, a “massively multi-model orchestration system.” Sounds like a lot of buzz words, but the bottom line is that Perplexity Computer is yet another agentic AI tool that can actually go out and do things. That puts it in the same category as Meta’s Manus AI and–of course–OpenClaw, the open-source AI tool that kicked off the recent “personal AI agent” craze just a matter of weeks ago. Work on Computer, which is currently available only to Perplexity Max users, began just last month as an “internal experiment,” Shevelenko wrote on LinkedIn. He attributed Computer’s speedy development to the fact that “work that would take weeks for a team was getting done overnight while we slept.” Computer is powered by a variety of different AI models, with Anthropic’s Claude Opus 4.6 running the “core reasoning engine,” Gemini handling deep research projects, Nano Banana creating images, Veo 3.1 crafting videos, Grok helping with “speed in lightweight tasks,” and ChatGPT 5.2 for “long-context recall and wide search.” Like OpenClaw, Perplexity Computer can be set loose on a project–anything from building a web-based dashboard or an app to creating a PowerPoint deck or an animated GIF–and it will devise a plan and eventually deliver a finished product, delegating sub-agents to toil on specific tasks, such as finding API keys, coding, or conducting secondary research. Unlike OpenClaw, Computer (which I’ve yet to try for myself) doesn’t live on your personal hardware. Instead, the Perplexity tool sits in the cloud and performs its work in a walled garden, interacting with outside services via a wide array of integrations. That’s a good thing if you’re worried about AI agents running amok on your system, but it also means Computer is bound by its sandbox, whereas OpenClaw can–if you let it–work directly on your devices. Another key difference is that you communicate with Perplexity Computer via the Perplexity app, whereas OpenClaw and now Manus AI offer chat via commonly used social messaging apps like WhatsApp, Discord, and Telegram.  Perplexity’s Sheveleno noted that he and his team “originally talked to [Computer] via Slack, since it felt more like a digital worker than just an agent,” but eventually decided that it’s “more like a computer, [so] we decided to name it, rebuild it, and launch it as a public product.” Read...

The BBC`s director general tells its Executive Complaints Unit to complete a fast-tracked investigation. Read...

Memory prices are insane, and it’s not just hurting consumers — PC makers have to deal with this crap, too. According to HP’s quarterly earnings call yesterday, the company is now spending approximately 35 percent of its PC bill of materials (that is, the price of all the parts in a computer) on RAM and storage. That’s about double what it was last year, 15-18 percent. That’s nowhere near the triple and quadruple prices consumers are seeing for RAM purchased at retail, but the math is different for HP, which gets its hardware much closer to the source. Even so, if the company sees “memory costs increase roughly 100% of sequentially,” according to CFO Karen Parkhill, it’s going to make a lot of other numbers go up in a bad way. While manufacturers like HP, Dell, and Asus are making money off of the “AI” boom by selling hardware to data centers, they’re also a lot more dependent upon regular consumers buying laptops and desktops. So they feel the pain of the market much more than the folks selling shovels in the gold rush — Nvidia, Micron, Samsung, et cetera. Reports indicate that regular PC manufacturers are scrambling for sources of less expensive memory, like looking into formerly regional memory producers in China. There are indications that the industry is, if not recovering, then at least leveling off. Some markets like Germany are finally seeing RAM prices start to go down from their stratospheric highs. This is estimated to be a correction not from the lack of supply itself, but from the increase in prices caused by “panic buying,” a trend observed in the general PC market. I don’t have enough data to make a call either way, but prices going down somewhere is encouraging. Prices for general PCs and other consumer tech that’s heavily reliant upon memory are expected to go up 20 percent across the board. The RAM crisis is predicted to go on for multiple years, unless the “AI” bubble pops. Read...

Scams keep coming at us—and they’re getting harder to spot. How? Scammers have begun making them more tailored to their marks. That is… us. Personalized scams, as security experts call them, use details about you in the hope of tricking you more easily. This information comes from illicit sources like data leaks and breaches, successful phishing attacks, compromised websites, and malware, as well as legitimate sources like marketing info, public records, and social media. As you might guess, the data range can span a pretty wide range, from location to shopping habits.  But what does a personalized scam look like? And how do you spot one? I brought these questions (and others) to a chat with Steve Grobman, Chief Technology Officer at McAfee—and it turns out that just like the data a scammer might have on you, the types of scams they craft fall under pretty broad umbrellas, too. The “general” personalized scam PCWorld These kinds of scams tend to target broad groups—like a specific geographic area. Toll scams have become personalized, for example. Before, messages claiming you had unpaid toll charges were generic. Now the texts will refer to your area’s toll authority and the name of the system, based on your phone number’s area code. If you’re not naturally a suspicious person, this updated approach may catch you off-guard. The language sounds more natural, despite being very broad. What changed? AI. Scammers can use AI to figure out regional information and incorporate it into messages quickly.  Scammers don’t have to know much about you to make this kind of connection. They’ll extrapolate it from your contact info. Think area code for a phone number or a specific service related to your email provider. For example, I’ve recently seen emails related to Google storage limits, claiming your files will be deleted soon because you ran out of space. The “specific” personalized scam Here’s where all those data leaks and breaches become a problem. Even when a data dump only involves details like name and location (like, say, from an address), a resulting scam message can sound much more official. It can address you by name, target your age bracket, and/or zero in on something specific to your region. The extra information allows for additional customization of the message. Grobman calls these “fill in the blank” scams, where a scary notice can easily swap in your name and a relevant entity to spook you. For my location, he described it as “___(name)____, the California Department of _________.” (A possible example would be: John, the California Department of Motor Vehicles has revoked your registration due to unpaid fees.) If matched well enough to your region, this approach could get you to click or otherwise fall for the scam, because it sounds realistic enough. The “hyperpersonalized” scam Scammers can target topical interests for their attacks.Wegovy This type of personalized scam is more insidious than outright creepy. (Mostly.) Grobman says these are “lifestyle” focused. Scammers use what they know of your habits—like sites you’ve visited or links you’ve clicked on—to figure out your interests. Then they’ll zero in to exploit that info. For example, if you’ve shown interest in weight loss, you could be targeted with a link to a fake weight loss drug. Hyperpersonalized scams can also take longer to build to the fraud—think romance scams, where the scammer uses information about you to build trust. Maybe they know where you went to school, and use that to start and build rapport. The more you share, the more they weave that into the relationship being built. Eventually, the requests for favors and money begin. Or shared communication, photos, and other details are then twisted into blackmail material, used to extort money in exchange for secrecy. Often, these kinds of scams can feel so personal—and so shameful to have fallen for one—that many victims won’t tell anyone they’ve been scammed. Previously, the young and the elderly were bigger targets for scammers, as they could prey on not just loneliness, but also lack of experience or diminished cognitive capabilities. But now, the threat for this to be widespread across all age brackets hangs lower than before… which is why we have to be on alert. What to do if you’ve been scammed First, take a deep breath. You might feel overwhelmed by your feelings—whether that’s shock, embarrassment, or shame—but that’s common and normal. Also common and normal: Making this kind of mistake. Falling for a scam can truly happen to anyone, even seasoned security professionals. Next, ask for help. The problem may seem huge at first, but getting help keeps the problem from spiraling into a huge mess. You can start with the FTC’s consumer advice page, which lists common scam scenarios and what steps to take afterward. Generally, you want to address the immediate problem first. Let’s say you used your credit card number on a scam site or wired money to a “special friend”—alert your bank about these fraudulent transactions right away. The faster you act, the faster you limit the damage. Worried about credit card or bank account fraud? Call your bank immediately!Cardmapr / Unsplash Or you shared your social security number and then realized your mistake. Add a security freeze to your credit reports immediately, and also add a security alert for good measure. (The freeze is the more powerful tool though, as it blocks anyone from checking or opening credit in your name until you temporarily allow access, aka “thaw” your report.) Take care of your emotional health, too. At a baseline, talking to a friend or family member who can help provide clarity or good feedback can help while you’re in a stew. You can also try your employer or even the police if you just need help in getting oriented. How to avoid personalized scams The grim reality is that personalized scams could become more common—the tools to help fraudsters keep improving, thanks to AI advances. (Thanks but no thanks, AI.) How fast that will happen remains to be seen—Grobman says scammers are business owners. They do what makes money, so a change in approach only comes when current efforts lose profitability. And that will happen the more awareness spreads and detection tools improve. (Remember, security experts also have AI available to them, too.) As that race continues to escalate, the shift toward more and more personalization will increase the difficulty of spotting legitimate messages among the fakes. Windows Security is a solid free antivirus option that Microsoft automatically keeps up to date.Foundry Fortunately, the best steps to protect yourself are also the easiest. Have antivirus software active on your PC. Be wary about installing apps on your computer or phone. Keep your software up to date, especially your browser. Use a password manager. Apps and services have begun to build in more safeguards and protections—think of it as a neighborhood watch approach to online security. The final piece of the puzzle? You. The sites you choose to visit, the software you download, the browser extensions you install, the links you click in email and messages—those all can increase or decrease your risk of getting caught in a scam, too. Surf the internet wisely. Read...

New Zealand Rugby’s general manager of professional rugby and performance, Chris Lendrum, will step down at the end of May. Read...

Director-General of Security Andrew Hampton said the designation was `something we should all be concerned about`. Read...

If your Intel processor requires a warranty return or support, the first “person” you’ll probably be dealing with at Intel will be an AI. Intel is rolling out “Ask Intel,” an addition to its Intel support site, that runs on Microsoft Copilot rather than on human intervention. Ask Intel will appear as part of support.intel.com, Intel sales executive Boji Tony announced on a LinkedIn post last week. Tony is the vice president and general manager of Intel sales enablement and support. Ask Intel is built on Microsoft Copilot Studio, and is “a new generative AI–powered virtual assistant for customer and partner support—one of the first of its kind in the semiconductor industry,” Tony said in the post, as reported by CRN. “With agentic AI capabilities, Ask Intel can open support cases on your behalf, check warranty coverage instantly, and connect you with live support agents when human support is needed,” Tony said. That Intel should replace at least some of its human customer support staff with AI shouldn’t be surprising. For one thing, Intel and others have been pushing AI solutions to replace humans at drive-through fast-food restaurants for years, such as at KFC. Now, the chipmaker is applying that same strategy to addressing your support questions, too. Foundry CRN reported that Intel began removing inbound customer support phone numbers in December, redirecting them to the support site. Naturally, Intel plans to make Ask Intel more central to the support experience over time. Today, Ask Intel isn’t the first thing you see when you visit Intel’s support site. When I began digging down through support options for Intel’s NUCs and Intel’s processors, the first time I experienced Ask Intel was in the “Live Chat” portion of the site. “This Virtual Assistant uses generative AI and answers may be inaccurate,” Ask Intel says. It also notes, “By using this feature, you agree that Intel and its third-party service provider may record, use, and store the contents of this dialog in accordance with ?Intel’s Privacy Notice.” When I used Ask Intel and asked to speak to a live representative, it first deflected, prompting me to describe the issue. In this case, I asked about crashing desktop CPUs, and Ask Intel first instructed me to download an updated graphics driver. I’m not entirely certain that would have solved my problem. It also suggested that I stress-test my processor, which may have exacerbated the issue. When I asked if stress-testing a possibly defective CPU was a good idea, Ask Intel then recommended that I update my motherboard’s BIOS instead. To be fair, we’re seeing AI chat options appear more and more in customer service. I’d be irritated if an AI screwed up my burger, but I’m sure a human manager could quickly fix it. But if I get the wrong advice from an AI and end up torching an expensive CPU, it might be a different story. Proceed carefully. Read...

After months of build-up, YouTube TV’s new Sports and genre plans feel underwhelming. YouTube started hyping up these plans in December, promising cheaper bundles with fewer channels you don’t care about. Sports fans, for instance, can get a package without news or entertainment channels, while sports haters can finally stop subsidizing expensive channels like ESPN. But while the new plans could save you some money, they’re not much different from other skinny bundles that DirecTV and Fubo offer already. In some cases, they might even be worse. False start First, a disclaimer: You probably can’t sign up for YouTube TV’s new plans yet. While they technically launched last week, YouTube says it’s “rolling these plans out slowly to ensure the best possible experience.” They may not be broadly available for several weeks. In the meantime, YouTube TV is still withholding some basic information. While it’s promising more than 10 genre plans in total, so far it’s only announced five of them: Sports Plan ($65/mo.): Local broadcast channels and national sports channels such as ESPN, FS1/FS2, TBS/TNT, NBC (including regional NBC Sports in select markets), Golf, NFL Network, and NBA TV, with ESPN Unlimited to be added in the fall. Sports + News Plan ($72/mo.): The above plan, plus CNN, MSNBC, Fox News, CSPAN, and business news channels. Entertainment Plan ($55/mo.): Local broadcast channels and general entertainment channels such as Hallmark, Comedy Central, HGTV, and Bravo. News + Entertainment + Family Plan ($70/mo.): Basically everything except sports, including kids channels such as Disney and Nickelodeon. Sports + News + Entertainment ($78 per month): Nearly the full YouTube TV package, but without kids channels. YouTube TV’s base plan, with more channels than any of the above options, remains available for $83 per month. Note that YouTube hasn’t released full channel lists for most of these packages (though Deadline got a channel list for the Sports package). It’s also unclear whether we’ll see any additional genre packages, or if the remaining five-plus options will just be different combinations of the Sports, News, Entertainment, and Family plans that YouTube has announced already. How YouTube TV’s Sports package compares Even with incomplete information, we can start to compare YouTube TV’s genre plans with the competition. The Sports plan, for instance, will be the cheapest way to combine local broadcasts and national sports channels if that’s all you want from a live TV service. At $65 per month, it’s $5 per month cheaper than DirecTV’s MySports plan, which launched last year, and $18 per month cheaper than YouTube TV’s standard plan. YouTube’s case gets stronger in the handful of markets that carry regional NBC Sports Networks. They’re included with YouTube TV’s Sports plan, but not DirecTV’s MySports package. (YouTube’s plans don’t include any other regional sports networks, while DirecTV offers a $20 per month MyHome Team add-on in select markets.) But if you want cable news, DirecTV’s MySports plan has an edge at $70 per month, versus $72 per month for YouTube TV’s Sports + News option. It also includes MLB Network and NHL TV, which YouTube’s bundle lacks. Jared Newman / Foundry (Click to enlarge or view on Google Sheets) YouTube TV’s Sports + News + Entertainment plan is interesting, in that it cuts out kids channels such as Nickelodeon, Disney Channel, and Cartoon Network. It’s only $5 per month cheaper than YouTube TV’s standard package, but that’s better than nothing for channels you might never watch. Those who want more price flexibility could look to Fubo Sports instead. At $56 per month, it’s cheaper than YouTube TV’s Sports plan, but it does not include NBC, TNT, TBS, or any regional sports channels. These bundles aren’t the only way to slice and dice sports coverage. You could also opt for some combination of ESPN Unlimited, Fox One, Peacock for NBC, Paramount+ for CBS, and HBO Max for TNT/TBS. But if you’re going to pay for all of those at the same time, you’re better off picking a bundle that includes all of their corresponding TV channels. YouTube TV’s non-sports plans YouTube TV’s other genre plans are a bit different from what DirecTV offers, at least from what we’ve seen so far. The $55 per month Entertainment plan, for instance, caters to folks who have no interest in sports but don’t want to give up local broadcast stations or general entertainment channels. Same goes for the $70 per month News + Entertainment + Family Plan. No other streaming TV packages like these exist on the market today. But as more kids tune into Netflix and YouTube, and as cable’s entertainment channels become bereft of original programming, the appeal may be limited. With its new genre plans, YouTube TV missed an opportunity to start bundling streaming services alongside traditional cable channels. That’s what DirecTV is doing with its $35 per month MyEntertainment package, which offers many of the same channels as YouTube’s Entertainment plan along with Disney+, Hulu, and HBO Max. And while DirecTV’s MyEntertainment doesn’t carry local channels, you can combine it with DirecTV MyNews for $75 per month total. That gets you local channels, cable news, entertainment, and a trio of streaming services. It’s a more compelling package than any of YouTube’s non-sports offerings. Slice and dice Given YouTube TV’s status as the largest live TV streaming service—one that might become bigger than major companies soon—I thought its bargaining power would result in packages that are clearly better than the competition. The reality is more nuanced. The new YouTube TV genre plans can save you money, but you’ll still have to carefully consider the alternatives and choose wisely. Sign up for Jared’s Cord Cutter Weekly newsletter for more streaming TV advice. Read...