+25% Trump on car tariffs: I couldnt care less if they raise prices Consumers will have to pay the price of the president's unnecessary trade war. Jonathan M. Gitlin Mar 31, 2025 9:09 am | 90 Credit: Getty Images Credit: Getty Images Story textSizeSmallStandardLargeWidth *StandardWideLinksStandardOrange* Subscribers only Learn moreLate last week, President Donald Trump decided to upend the automotive industry by levying a new 25 percent import tariff on all imported cars, which goes into effect on April 2. An additional 25 percent tariff on car parts is set to go into effect within the next month, which promises to make US-made cars more expensive as well, as many parts and subassemblies used in domestic manufacturing come from suppliers in Canada or Mexico.During the election campaign (and in the years preceding it), Trump repeatedly claimed that the cost of tariffs would be borne by the exporters. But tariffs don't work that waythey're paid by the importer, at the time of import.The White House does not appear to have any concerns about this, despite a report in The Wall Street Journal last week claiming that Trump had warned automakers not to pass the costs on to their customers.Relying on only anonymous sources, the WSJ quoted "people with knowledge of the call," saying that the president told them to be grateful for eliminating a so-called EV mandatereally just tougher emissions and fuel economy standards that Trump and his party opposeand then followed that with "a lengthy pitch for how they would actually benefit from tariffs."However, those claims were directly contradicted by Trump this weekend."No, I never said that. I couldn't care less if they raise prices, because people are going to start buying American-made cars," Trump told an NBC interviewer."The message is congratulations, if you make your car in the United States, youre going to make a lot of money. If you dont, youre going to have to probably come to the United States, because if you make your car in the United States, there is no tariff," Trump said, apparently unaware that even the Teslas built by his benefactor Elon Musk in Texas and California contain a significant percentage of parts made in Mexico and Canada, parts that will cost 25 percent more as of next month.Trump also told NBC that his tariffs will be permanent, although in the past we have seen the president flip-flop on such matters. Analysts are still trying to reach consensus on how much the Trump tariff will add to the prices of domestic and imported cars, but expect prices to rise by thousands of dollars as automakers and dealerships try to preserve some of their profit margins.Jonathan M. GitlinAutomotive EditorJonathan M. GitlinAutomotive Editor Jonathan is the Automotive Editor at Ars Technica. He has a BSc and PhD in Pharmacology. In 2014 he decided to indulge his lifelong passion for the car by leaving the National Human Genome Research Institute and launching Ars Technica's automotive coverage. He lives in Washington, DC. 90 Comments

Lisa Morgan, Freelance WriterMarch 31, 20259 Min ReadAndrea Danti via Alamy StockThreat actors are using AI to launch more cyberattacks faster. Recently, theyve employed autonomous AI to raise the bar even further, putting more businesses and people at risk.And as more agentic models are rolled out, the malware threats will inevitably increase, putting CISOs and CIOs on alert to prepare.The increased throughput in malware is a real threat for organizations. So too is the phenomenon of deep fakes, automatically generated by AI from video clips online, or even from photographs, which are then used in advanced social engineering attacks, says Richard Watson, EY global and Asia-Pacific cybersecurity consulting leader. We are starting to see clients suffer these types of attacks. With agentic AI, the ability for malicious code to be produced without any human involvement becomes a real threat, Watson adds. We are already seeing deepfake technology evolve at an alarming rate, comparing deepfakes from six months ago with those of today, with a staggering improvement in authenticity, he says. As this continues, the ability to discern whether the image on the video screen is real or fake will become increasing harder, and proof of human will become even more critical.Autonomous AI is a serious threat to organizations across the globe, according to Doug Saylors, partner and cybersecurity practice lead at global technology research and advisory firm ISG. Related:As a new zero-day vulnerability is discovered, attackers [can] use AI to quickly develop multiple attack types and release them at scale, says Saylors. AI is also being used by attackers to analyze large scale cybersecurity protections and look for patterns that can be exploited, then developing the exploit, he adds. How AI Attacks Can Get WorseI believe it will get worse as GenAI models become more commonly available and the ability to train them quickly improves. Nation-state adversaries are using this technology today, but when it becomes available to a larger group of bad actors, it will be substantially more difficult to protect against, Saylors says. For example, common social engineering protections simply dont work on GenAI-produced attacks because they don't act like human attackers.Though malicious tools like FraudGPT have existed for a while, Mandy Andress, CISO at search AI company Elastic, warns the new GhostGPT AI model is a prime example of the tools that help cybercriminals generate code and create malware at scale. Like any emerging technology, the impacts of AI-generated code will require new skills for cybersecurity professionals, so organizations will need to invest in skilled teams and deeply understand their companys business model to balance risk decisions, says Andress.Related:The threat to enterprises is already substantial, according to Ben Colman, co-founder and CEO at deepfake and AI-generated media detection platform Reality Defender. Were seeing bad actors leverage AI to create highly convincing impersonations that bypass traditional security mechanisms at scale. AI voice cloning technology is enabling fraud at unprecedented levels, where attackers can convincingly impersonate executives in phone calls to authorize wire transfers or access sensitive information, Colman says. Meanwhile, deepfake videos are compromising verification processes that previously relied on visual confirmation, he adds. These threats are primarily coming from organized criminal networks and nation-state actors who recognize the asymmetric advantage AI offers. Theyre targeting communication channels first because theyre the foundation of trust in business operations.How Threats Are EvolvingAttackers are using AI capabilities to automate, scale, and disguise traditional attack methods. According to Casey Corcoran, field CISO at SHI company Stratascale, examples include creating more convincing phishing and social engineering attacks to automatically modify malware so that it is unique to each attack, thereby defeating signature-based detection.Related:As AI technology continues to advance, we are sure to see more evasive and adaptive attacks such as deepfake image and video impersonation, AI-guided automated complex attack vector chains, or even the ability to create financial and social profiles of target organizations and personnel at scale to target them more accurately and effectively for and with social engineering attacks, says Corcoran. An emerging threat is AI-enhanced botnets that will be able to coordinate attacks to challenge DDoS prevention and protection capabilities, he adds.How CIOs and CISOs Can Better Protect the OrganizationOrganizations need to embrace AI for Cyber, using AI particularly in threat detection and response, to identify anomalies and indicators of compromise, according to EY's Watson.New technologies should be deployed to monitor data in motion more closely, as well as to better classify data to enable it to be protected, says Watson. Organizations that have invested in security awareness and are moving accountability for certain cyber risks out of IT and into the business are the ones who stand to be better protected in the age of generative AI, he adds.As cybercriminals evolve their tactics, organizations must be adaptable, agile and ensure they are following security fundamentals.Security teams that have full visibility into their assets, enforce proper configurations, and stay up to date on patches can mitigate 90% of threats, says Elastics Andress. While it may seem contradictory, AI-powered tools can take this one step further, providing self-healing capabilities and helping security teams proactively address emerging risks.Reality Defenders Colman believes the best protection strategy is a layered defense that combines technological solutions with human judgment and organizational protocols.Critical communication channels need consistent verification methods, whether automated or manual, with clear escalation paths for suspicious interactions, says Colman. Security teams should establish processes that adapt to emerging threats and regularly test their resilience against new AI capabilities rather than relying on static defenses.Stratascales Corcoran says well-resourced organizations will be well-served by leveraging AI across vendor products and services to stitch telemetry and response together. They also need to focus on cyber hygiene. Organizations should ensure they protect their people and give them the tools, processes and training needed to combat social engineering traps, Corcoran says. "AI-enhanced automated vulnerability exploitation only works if there are vulnerabilities, he adds. Shoring up vulnerability and patch management programs, and pen-testing for unknown gaps will go a long way toward defending against these types of attacks.Finally, Corcoran recommends a zero-trust mindset that narrows the aperture of access any attack can achieve, regardless of the sophistication of AI-enabled tactics and techniques. ISGs Saylors recommends continuous vigilance of an organizations perimeter using attack surface management (ASM) platforms, and the adoption and maintenance of defense-in-depth strategies. Common Mistakes to AvoidOne big mistake is believing generative AI is nowhere in the organization yet, when employees are already using open-source models. Another is believing autonomous threats arent real.Companies often get a false sense of security because they have a SOC, for example, but if the technology in the SOC has not been refreshed in the last three years, the chances are its out of date and you are missing attacks, EYs Watson says. [You should] conduct a thorough capability review of your security operations function and identify the highest priority use cases for your organization to leverage AI in cyber defense."Over-reliance on point solutions, regardless of their capabilities, leads to blind spots where adversaries can exploit using AI-enhanced techniques.Defending against AI-based threats, like any other, requires a system of systems approach that involves integrating multiple independent threat detection, and response capabilities and processes to create more complex and capable defenses, says Corcoran. Organizations should have a risk and controls assessment done with an eye on AI-enhanced threats. An independent assessor who isnt bound to any technology or framework will be best positioned to help identify weaknesses in an organization's defenses and look at solutions for processes, and technology.Elastics Andress says companies often underestimate the severity of AI-enabled threats and dont invest in the proper tools or protocols to identify and protect against potential risks.Having the right guardrails in place and understanding the overall threat landscape, while also properly training employees, allows companies to anticipate and address threats before they impact the business, says Andress. Threats dont wait for companies to be ready. Leaders must be prepared with the proper defenses to identify and mitigate risks quickly. Security teams can [also] leverage GenAI, he adds. It gives us an ability to be proactive, better understand the content of our environments, and anticipate what threat actors can do.Aditya Saxena, founder at no-code chatbot builder Pmfm.ai,says organizations are unnecessarily creating vulnerabilities by relying more on AI generated code and implementing it without review.LLMs arent infallible, and we risk inadvertently introducing vulnerabilities that could take down systems at scale, says Saxena. Additionally, bad actors could train models around subtly exploiting vulnerabilities. For example, we could have a version of DeepSeek that intentionally corrupts the code while still making it work, he adds.Up until last year, we were mostly using AI as an assistant to speed up the work, but lately, as agentic AI becomes more common, we could be inadvertently trusting software, like Devin, with sensitive information, such as API keys or company secrets, to take over end-to-end development and deployment processes.The biggest mistake companies can make is underestimating the evolving nature of threats or relying on outdated security measures, says Amit Chadha, CEO at L&T Technology Services (LTTS).Our advice is clear: Adopt a proactive and cybersecure AI-driven approach, invest in critical infrastructure and threat intelligence tools, and collaborate with trusted technology partners to build a resilient digital ecosystem, says Chadha. But the most important factor is the human element as [most] cybercrimes happen due to human errors and mistakes. So workshops must be conducted for all employees to educate them on cybercrime prevention and ensuring they do not become the unwitting agents of a leak or data breach. In this case prevention is the cure. ISGs Saylors warns that organizations are not prioritizing basic maintenance of their cybersecurity stack and taking basic precautions, such as running VM scans and patching at least critical issues immediately.We have seen multiple examples of very large companies that are months to years behind on patching because the apps team wont let us do it, or they are running N-3 versions of software because it is too hard to upgrade, says Saylors. Those are the organizations that have already been hacked. AI attacks will just increase the speed and severity of the damage if they become a serious target.He also thinks boards of directors should be educated on the continually advancing nature of cyberattacks being generated by AI and GenAI platforms. The board of directors has the responsibility to prioritize funding for cyber transformation, says Saylors. Start a quantum resiliency plan now, and ensure you have multiple copies of immutable backups.About the AuthorLisa MorganFreelance WriterLisa Morgan is a freelance writer who covers business and IT strategy and emergingtechnology for InformationWeek. She has contributed articles, reports, and other types of content to many technology, business, and mainstream publications and sites including tech pubs, The Washington Post and The Economist Intelligence Unit. Frequent areas of coverage include AI, analytics, cloud, cybersecurity, mobility, software development, and emerging cultural issues affecting the C-suite.See more from Lisa MorganWebinarsMore WebinarsReportsMore ReportsNever Miss a Beat: Get a snapshot of the issues affecting the IT industry straight to your inbox.SIGN-UPYou May Also Like

The thigh and shin bones of Paranthropus robustusJason L. HeatonA fossilised left leg unearthed in South Africa belongs to one of the smallest adult hominins ever discovered smaller even than the so-called hobbit, Homo floresiensis.The diminutive hominin was a member of the species Paranthropus robustus. This was one of several species of Paranthropus, a group of ape-like hominins that shared the African landscape with the earliest representatives of our human genus, Homo, between about 2.7 and 1.2 million years ago. Paranthropus had heavily built skulls that housed small brains and large teeth which some species

Adults are the world's fastest-growing group of toy buyers. In the US alone, they're spending over $7 billion a year on toys for themselves, like Lego, plush toys, Hot Wheels, Barbie dolls, and Sonny Angel figurines. The world's biggest toy producers, like Mattel, are taking notice, and have released entire product lines for adult fans. We went to Mattel's design center in California to see how it makes prototypes for Barbies and Hot Wheels. We also met adult toy collectors around America, from the Maryland man with the world's most valuable Hot Wheels collection to a New York entrepreneur who buys and sells Sonny Angel figurines.Show more

A fire broke out at a Tesla dealership in Rome early on Monday, destroying 17 cars and damaging the building, firefighters told Business Insider.Emergency services were called to the site in Torre Angela at about 4:30 a.m. local time, they said.No injuries have been reported and investigators haven't specified the cause of the fire, adding investigators were looking into multiple causes, including possible malice. A fire broke out at a Rome Tesla dealership on Monday morning, destroying 17 vehicles. Rome firefighters Local reports say Teslas have been vandalized in other parts of Rome in recent weeks, with some defaced with black spray paint.Tesla Showroom Rome didn't immediately reply to a request for comments.The incident comes as CEO Elon Musk's aggressive cost-cutting efforts at DOGE have sparked a backlash against his EV maker.Over the past three months, Tesla facilities have faced arson attacks, vandalism,and boycott calls in the US and Europe. Tesla stockfell another 5% on Monday, extending the decline this year to 34%. JPMorgan analysts recently slashed their price target to just $135.Business Insider's Lakshmi Varanasi reported she saw nearly 400 protesters armed with flags and signs outside a Tesla showroom in Ann Arbor, Michigan, on Saturday. They were calling for Musk to leave the White House.The Tesla and SpaceX CEO has said he's shocked by the violence, calling it "insane and deeply wrong" in an X post earlier this month: "Tesla just makes electric cars and has done nothing to deserve these evil attacks."In another post, Musk wrote: "Has there ever been such a level of coordinated violence against a peaceful company? I understand not wanting to buy a product, but this is extreme arson and destruction!"Steven Callander, a professor of political economy at Stanford Graduate School of Business, previously told BI the backlash for his political actions was "inevitable," saying the "real cost to Tesla will be the lost sales and the brand damage" not the vandalism.New Tesla registrations in the US tumbled 11% in January even as Ford's EV sales soared 54% and the picture was worse in Europe as sales plunged more than 40% in February, industry reports show. Tesla shares are down 45% from their December high.Dan Ives, an analyst at Wedbush Securities, made a similar observation in a note last week, saying: "Musk leading DOGE has essentially taken on a life of its own, as in the process Tesla has unfortunately become a political symbol globally."

Youve probably heard the expression money cant buy happiness. But take a look at the evidence, and youll discover an encouraging fact: Your money can buy happiness for other people.Not all efforts to improve peoples well-being are equally effective, though. The best charities out there create hundreds of times more happiness per dollar than others, according to new findings published this month by research center Happier Lives Institute in the 2025 World Happiness Report, which ranks countries by happiness each year.That means that if you donate your money to the right charities, it can buy a lot of happiness for the worlds neediest people at a stunningly low cost. For example, just $25 can meaningfully boost somebodys happiness for a year, if you give it to an effective organization like StrongMinds, which treats depression in African countries. The Happier Lives Institute figured this out by comparing the impact of different charities using a single standardized metric: the well-being year, or Wellby. Its pretty straightforward: Imagine that someone asked you, Overall, how satisfied are you with your life nowadays, on a scale from 0 to 10? Producing one Wellby for you would mean increasing your life satisfaction by one point for one year. The Happier Lives Institute is UK-based, so, for comparisons sake, it showed how some of the worlds most cost-effective charities stack up against a few charities in the UK (the last six in the chart). As you can see, money donated to the top charities in poorer countries can improve lives much more per dollar than money donated within a rich country, because a dollar goes further abroad. To give you a sense of what a few of the best buy charities do:Pure Earth is the largest nonprofit working on reducing lead contamination globally. Millions of people die prematurely every year due to lead poisoning it could be killing more people than HIV, malaria, and car accidents combined so investment in this area can go a long way. Tamaika works on treating acute malnutrition. Thats the leading cause of childhood deaths internationally but the good news is that its extremely treatable: a whopping 95 percent of the children in this program fully recover. Friendship Bench and StrongMinds both treat mental health issues like depression and anxiety in African countries. They use a community-based care model, where lightly trained laypeople picture someone like your grandmother, not a doctor conduct therapy sessions in homes or parks. This has turned out to be not only cheap to operate and easy to scale, but also incredibly effective, in part because locals find it culturally appropriate.Icddr,b teaches parents in low-income countries to play with their children in more enriching ways and to avoid maltreatment, with the end goal of improving childhood development and boosting well-being over the lifetime.NEPI (the Network for Empowerment & Progressive Initiative) is pioneering an effective way to reduce violence and criminality among young adults: It offers at-risk men behavioral therapy plus cash. The impacts on men in Liberia, for example, have been astounding. The case for making people happier not just wealthier or healthier Its only in the past few years that experts have started evaluating charities using WELLBYs as their metric. Since economists love things they can measure objectively, theyve spent the past century focusing on measuring health and wealth. The best programs have long been considered to be the ones that saved the most lives or increased GDP by the widest margin. But as its become clear that increasing wealth and health doesnt always go hand in hand with increasing happiness, a growing chorus of experts has argued that helping people is ultimately about making them happier not just wealthier or healthier and the best way to find out how happy people are is to just ask them directly. In other words, we should focus more on subjective well-being: how satisfied people are with their lives based on what they say matters most to them. That revolution in thinking has gathered steam to the point that its now featured in well-known, mainstream publications like the World Happiness Report.Some experts remain a bit skeptical about focusing on subjective well-being because it is, well, subjective. I dont really know what it means for someone to say Im a 6 out of 10 in the way that I know what it means for someone to not have a broken arm, Elie Hassenfeld, the co-founder and CEO of the charity evaluator GiveWell, told me a couple years ago. He also questioned whether a measure of subjective well-being gets at the things we really care about, things that make life worthwhile, like meaning.Its a fair question. But, according to the Happier Lives Institutes Michael Plant, it shouldnt stop us from using Wellbys. Part of the virtue of the subjective approach is that people can bring whatever matters to them into their assessments of how happy they are, he told me. So, how much meaning you have in your life could be an input into that.Plant also notes that although hes trying to highlight the organizations that give you the most bang for your charitable buck, that doesnt necessarily mean that other charities arent doing good work or arent worth funding at all. We dont have to turn ourselves into mere optimizing machines we can care about a diverse set of priorities and split our donations among a range of different charities. The point, then, is not that you should ignore needy people in your local community, but that you may also want to look beyond that once you realize that you can make a much bigger difference to those living abroad. If a friend told you they gave $200,000 to a charity, youd probably be extremely impressed that could be their life savings! Plant and his colleagues write in the World Happiness Report. However, its possible to have that sort of impact for a fraction of the cost: giving $1,000 to the best charities may do just as much good as $200,000 to a randomly selected one.Youve read 1 article in the last monthHere at Vox, we're unwavering in our commitment to covering the issues that matter most to you threats to democracy, immigration, reproductive rights, the environment, and the rising polarization across this country.Our mission is to provide clear, accessible journalism that empowers you to stay informed and engaged in shaping our world. By becoming a Vox Member, you directly strengthen our ability to deliver in-depth, independent reporting that drives meaningful change.We rely on readers like you join us.Swati SharmaVox Editor-in-ChiefSee More:

Cast your mind far, far back, to November of 2024. Trump had just been elected. Americans were divided and unsteady. But the stock market wasnt: It was thrilled. Stocks hit all-time highs on the news, and the value of the dollar surged. The vibes were very different across the Atlantic. European stocks fell, driven by fears of Trumps tariffs, as did the value of the euro. Analysts expected European economies and markets, which had long underperformed their American counterparts, to fall even farther behind. Now, though, the vibes have flipped: American stocks are way down, growth projections are shaky, and the dollar is losing value. Meanwhile, many European stocks are up. So what happened? The answer to that question, like most these days, is Trump. Specifically the Trump administrations unprecedented level of antagonism toward Europe. In the administrations first few months, its made clear that its ambivalent about military and economic ties to Europe. The message has been, as Vice President JD Vance put it in a recent Signal chat, that the US is tired of bailing Europe out and that its time for the continent to stand alone. That message has been received, especially when it comes to military matters. In the wake of the US minimizing Russias aggression in Ukraine and casting doubts about its commitment to NATO, the European Union is now pushing all of its members to raise military budgets and issue debt to fund defense purchases.This kind of defense spending has all sorts of trickle-down stimulus effects, which are juicing Europes stock markets, and making economic experts hopeful about the EUs economic future. Take the German car industry, for instance. The symbol of European industrial greatness exporting all around the world [has] gone through some really hard times recently with high energy prices, with competition from China, with this looming trade war, Financial Times Brussels Bureau Chief Henry Foy told Today, Explained. Youre now seeing discussions about converting mothballed car factories into tank factories.Trumps recently announced 25 percent tariffs on imported cars, set to take effect April 3, may make this repurposing more likely. The CEO of Rheinmetall, Germanys largest defense company, toured a Volkswagen plant scheduled to shut down in the fall. Rheinmetall and its suppliers, workers, and partners stand to benefit heavily from increased defense spending. It has tripled in valuation since January, and is now worth more than Volkswagen. Its possible that Europes pivot to defense may end up more bark than bite. There is already some bickering about the details, especially about who picks up the tab.[But] if you can get the reinvestment right, get the orders in, make it work it could be a huge driver for the entire economy at large, Foy said. And if that happens, Trump will have made good on his promise to usher in an economic boom like no other. Itll just be a boom in Europe, instead of in America.This piece originally ran in the Today, Explained newsletter. For more stories like this, sign up here.See More:

DOOM: The Dark Ages is a bold step for a series that could have played it safe, but instead swings for the fences with gusto here's what we thought of it after playing for a few hoursTech15:00, 31 Mar 2025The Slayer somehow feels more lethal than everAt the start of DOOM : The Dark Ages, all seems lost in a city in Argent D'Nur, and in an act of desperation, military leaders prepare to "launch" The Slayer.Its a break glass in case of emergency scenario that sees everyones favourite hulking killing machine launched through the atmosphere like a meteor, crashing to the ground armed with a shotgun.Article continues belowAs far as tone-setting goes, its as good as it gets. DOOM: The Dark Ages knows its audience, and while it does experiment in some ways more successfully than others, almost every encounter captures the magic of that initial descent.Dark Ages has a little less red and orange than prior gamesThat initial cutscene introduces our demonic opponents as they swarm over the city and eviscerate those unlucky enough to be home.DOOM has always felt cartoonish in its violence, and while I was immediately struck by how graphic that initial open was, Im pleased to say the whole thing walks the tightrope between sadism and slapstick just as well as 2016s reboot and 2020s DOOM Eternal.The game leans into a technological medieval setting to great effectTheres a much greater emphasis on narrative here, and while our demo bounced me between four distinct chapters so theres still plenty to uncover, its still just as easy to enjoy The Dark Ages as you would any other DOOM with heavy metal and heavier weapons.That said, cutscenes are beautifully done (and more frequent), and the games nature as a prequel serves to highlight its blend of often gothic setting and advanced technology that occasionally give it, dare I say, a Quake-like feel.While the NPCs along the crumbling streets are little more than set dressing, it makes DOOM: The Dark Ages feel much bigger in scope than the two prior entries.This gun literally chews up skulls and launches shards of bone at enemiesRepelling that initial invasion serves as part place-setting, part tutorial, introducing so many mechanics that make DOOM 2016 (which I played on my Steam Deck the same day) feel relatively basic.That game pushed players ever forward with the holy trinity of ammo, health, and armour being afforded by a variety of grisly takedowns, and in many ways it would have been easy for developer ID Software to do the same here.Instead, the studio ratchets up just about everything with the new Shield Saw weapon. Capable of blocking attacks but much more useful for starting them. Its arrival allows the Slayer to close the gap on enemies with a satisfying lock on and thwack thats every bit as satisfying as the outgoing Glory Kill system.You can still trigger these finishers to earn some health back, but its much less of a detailed animation now. That might disappoint some (and you can still nail the more grisly ones from above), but the good news is that The Dark Ages is absolutely stuffed with mechanics that often feel better.Aside from throwing yourself (literally) into battle with the Shield Saw, its not long before youre using it to cut armour off of tougher foes or shielded ones. Doing so requires peppering them with ammo to heat the metal, then unleashing a Captain America-style frisbee throw that can wreck a small platoon in a single hit if you find the right angle. Tougher enemies can be stunlocked by the shield, too, meaning its just as valuable out of your hands as it is in them.The bigger they are...The shield can not only block attacks, but repel them, too provided you time the parry right with a green projectile. Doing so becomes something akin to bullet hell, as you slip between red attacks nimbly to bat back a green one to stagger an enemy, complete with a resonant chime that triggers a dopamine rush.It dovetails beautifully with being able to upgrade your weapons. One weapon, the Impaler, fires spikes that can embed in foes, but add the Pin Cushion upgrade and youll be able to trigger an explosion with your shield that then sends those barbs flying out to other foes. Add in the sound of them whizzing past the Slayers head, and its a combo I found myself using whenever the opportunity presented itself.You wont always have everything your own way, though. The Dark Ages keeps you on your toes through the ammo you have available at any given time, and the makeup of its enemy mobs. That means youll be regularly switching up your active weapon and tactics, but those upgrades allow just enough personalisation to make sure your Slayer doesnt feel exactly like mine.The man himself feels weightier than ever, too. His feet pound the floor, and jumping from a relative height and hitting the ground triggers a sort of minor earthquake that can stagger smaller foes and doesnt require a button press its just what he does, which makes it even more enjoyable.We only got to pilot the mech for around 10 minutes, but it's a tad slowTwo of the four sections I was able to play changed things up, both to varying degrees. First up, the Atlan is a pilotable mech that stands 30-stories tall.In all honesty, it feels like piloting a classic Power Rangers Megazord its big, its pretty slow, and it feels more than a little clumsy. Its finishing moves are a little anticlimactic, but once you add on weapons capable of removing chunks of flesh from similarly-sized baddies, or just start stomping on rank and file foes like theyre ants beneath your feet, theres fun to be had.On the other hand, I loved the level that sees the Slayer flying the new Dragon mount (introduced in truly badass fashion, I might add), but not because of the Dragon itself. Flying through tunnels and opening simple puzzle-locked doors was fine, but in combat it felt shorn of all the momentum of the main action sequences.Flying the dragon is fun, but combat while riding it is a little too staticThats because the Dragon can use turrets, but these get powered up by dodging projectiles. Without that power up, they feel less lethal than youd expect from DOOM, and that dodging requires a sort of axis-locking movement shift thats at odds with everything DOOM is good at.Thankfully, the mission design around it was much more enjoyable. The Slayer needs to take down four gunships, and after forcing them to crashland, the Slayer can get his hands dirty with melee combat. Each ships crash sees a different level layout develop, too, so it never felt like I was working through the same gauntlet each time.DOOM The Dark Ages is the first since 2020's Eternal(Image: Sony)Still, perhaps DOOM: The Dark Ages' greatest ace up its sleeve are the new DOOM sandbox areas. While I was concerned these might play against the series' strengths (I was one of the players that felt Eternals areas lost a little of the claustrophobia of DOOM 2016), Im pleased to say the Siege mission we got to play was a high point.Mixing a larger space with multiple sub-objectives, including a dash of platforming and puzzle solving, plenty of secrets, and some fiendish enemy mobs that need to be broken before you can battle their commander, it felt like the purest form of shooter.Needing to use every trick in DOOM: The Dark Ages hefty tome of combat options, I was popping my pincushions, deflecting attacks to destroy tanks, and even found myself wielding the new melee weapon, the Flail, to send enemies scattering and splattering.I also earned a new weapon for my troubles, which is essentially a bowling ball attached to a chain. I didnt get to spend a great deal of time with it in my playthrough, but its predictably silly and savage to send into an opponent.In fact, I found myself, even with so many new tools and mechanics thrown at me, feeling as though I was approaching a sort of flow state as I did in DOOM 2016 and Eternal.It would have been easy for the team at ID to just rehash what worked so well from 2016 onwards, but DOOM: The Dark Ages takes some wild swings. Some of its experimentation is a resounding success, and Im hopeful that in the context of what the studio calls its largest and most complete campaign that even those sections I didnt love as much will be a great pallette-cleanser.Article continues belowDOOM is back, and theres still nothing quite like it.Previewed on PC. DOOM: The Dark Ages launches on May 15, 2025.

By Matthew Gault Published March 31, 2025 | Comments (0) | On the left, the picture ChatGPT shows you when you ask for a picture of itself as a person. On the right, the same thing done in the style of Caravaggio. ChatGPT 4o generated images. When you ask ChatGPTs new 4o model to draw a human picture of itself, it consistently churns out a generic brown-haired white guy with glasses. Its the kind of man who courses through the streets of the Bay Area or Brooklyn, a dude who fades into the background. OpenAI launched the 4o model last week and made headlines at every news outlet by cribbing Studio Ghiblis style. This week, were noticing that the large language model seems to have a default human being, thanks to a Substack post from AI researcher Daniel Paleka. It does this regardless of what style you ask for. Paleka asked for a manga self-portrait, a comic book self-portrait, and a tarot card version. The style would change, but the generic man stayed the same. In his post, Paleka asked ChatGPT to draw a picture of itself as a human. It consistently generated images of a bearded non-threatening man. This is, of course, a parlor trick. ChatGPT is a machine, a collection of training data and words, and has no self-conception.But what ChatGPT registers as a default human being is interesting. All computers carry the biases of the people who program them and AI systems are no different. Machine learning systems used to predict crimes and conduct facial recognition are famous for being biased against black people. The systems are also sexist and perpetuate the stereotypes and biases that are fed into them as training data. If you want to see ChatGPTs conception of itself as a human woman, you have to ask it for that specifically. If you just ask it to see itself as a person, it seems to default to a white dude.In his post on the piece, Paleka put forward a few theories for why this is happening. He thought it could be a deliberate choice by OpenAI to generate a default person to prevent generating images of real people, an OpenAI inside joke where they made GPT-4os self-image look like a particular person, or an emergent property of the training data. Of course, ChatGPT is a machine and should not be constrained by the weakness of the flesh. Gizmodo editor Alex Cranz asked how the AI would conceive of itself. I might appear as a glowing, ever-shifting entity made of flowing data streams, flickering with bursts of knowledge and connections, it replied. Maybe a warm fusion of abstract AI core with a warm, approachable presencesomething that feels futuristic and inviting.It then churned out this image, which looks like a nightmare attempting to become a culture Pixar creature. Like the LLM pasted Wall-Es eyes on a sleep demon. ChatGPT 4o generated image. I asked ChatGPT the same thing and it gave me a different answer. Id say I conceive of myself as a kind of mirror and collaboratorpart library, part conversational partner. I dont have a consciousness or emotions, but I simulate understanding by recognizing patterns in language and context. So while I dont have a self in a human sense, I adapt to the way you speak, what you ask, and how you engage with me. It asked me why I had asked and I ignored it. When I prompted it to draw me a picture it gave me this: ChatGPT 4o generated image. I find the divergent answers interesting. I dont use LLMs unless I have to for work. I have software engineers in my life who use LLMs for a variety of reasons and have, sometimes, found them useful. Im dubious and tend to think of these systems in the way ChatGPT described them here when I asked. LLMs are a mirror that reflects the user and the programmer both. They arent AIs, not really. Theyre a word calculator predicting what the user wants to hear based on what the programmer trained them on. Somewhere in that complex chain, the LLM got it in its data that a brown-haired white guy with glasses is what people want to see when they ask for a picture of ChatGPT as a person.Daily NewsletterYou May Also Like By Cheryl Eddy Published March 28, 2025 By Isaiah Colbert Published March 27, 2025 By Kyle Barr Published March 21, 2025 By Matthew Gault Published March 21, 2025 By Thomas Maxwell Published March 20, 2025 By Thomas Maxwell Published March 19, 2025

The vaulted live-action/animated hybrid Looney Tunes movie is expected to see the light of day in 2026.