Using multiple expert personas in generative AI is relatively easy to do and has sizable payoffs.gettyIn todays column, I showcase a valuable prompting technique that uses multiple expert personas to push generative AI and large language models (LLMs) toward first-class or top-notch answers. The approach is straightforward. You invoke the intrinsic capabilities of AI LLMs to undertake persona simulations, and cleverly combine this facility with a focus on the personas as experts in whatever field of inquiry you are interested in. Various crucial upsides and downsides need to be observed.Lets talk about it.This analysis of an innovative AI breakthrough is part of my ongoing Forbes column coverage on the latest in AI including identifying and explaining various impactful AI complexities (see the link here).Prompt Engineering And PersonasIn a previous posting I explored over fifty prompt engineering techniques and methods, see the link here. Among those myriad approaches was the use of personas, including individual personas and multiple personas, as depicted at the link here, and the much larger scale mega-personas at the link here. Personas are a powerful feature available in LLMs, yet few users seem to be familiar with the circumstances under which they should consider invoking the capability.A persona consists of telling generative AI to pretend to be someone and simulate what that person might know or say. No special setup or elaborate instructions are needed to get this undertaken. I will be providing you in a moment with prompts that show how this is readily performed.A quick example of the value of personas might be helpful here.One of the most popularly invoked personas entails generative AI pretending to be Abraham Lincoln. A teacher might tell a generative AI app such as ChatGPT to simulate the nature of Honest Abe. Students then access the pretense or persona. In an amazing flair, the AI seemingly responds as we assume Lincoln might have responded.MORE FOR YOUOf course, this is based simply on the numerous speeches, written materials, and other collected writings that suggest what he was like. The AI has pattern-matched computationally on those works and mimics what Lincolns tone and remarks might be. Anyone using a generative AI persona needs to keep their wits about them and realize that the conversation or engagement is nothing more than a mimicry or imitation. Though the AI appears to often convincingly fake the nature of the person, it is all still a computational simulation.Generative AI And Subject Matter ExpertiseA clever way to lean into personas consists of telling generative AI to pretend to be an expert in some field of study.Imagine that you are interested in climate science as a specific domain. You could tell generative AI to pretend to be an expert in climate science. Notice that you dont have to name a particular person, such as in the case of naming Abraham Lincoln as the subject of the persona. A persona can be unnamed. If the persona is not based on a known person, youll need to be mindful and state what the persona is supposed to be modeled on.I might tell generative AI to pretend to be a climate science expert. Voila, that alone would be sufficient to get the AI to simulate that specialty persona. One issue to keep in mind is whether the generative AI that you are using has sufficient data and has sufficiently patterned on that data to adequately represent the field of interest. Be cautious since the AI might be quite shallow and yet portray the expertise as though it is in-depth.For whatever kind of expertise you want to base a persona on, a vital question is whether the AI has been data-trained extensively on that topic. Most of the major generative AI apps are broadly trained across a wide swath of the Internet. This tends to make the AI so-called mile-long and an inch deep in terms of expertise.Do not assume that some desired expertise is always at the ready.It is usually wise to ask the AI what level of proficiency it seems to have in whatever topic you are exploring. This doesnt guarantee that the AI will be forthright, and you might get either a bland answer or a false or misleading response. If possible, consider asking direct questions on the topic and have a basis to compare the answers, such as doing online searches or having in-hand materials to corroborate what the AI opines on the topic.Another common means of boosting AI in a field of interest would be to feed or import content on the topic directly into the generative AI. The use of retrieval-augmented generation (RAG) and in-context modeling can aid the AI in moving up the ladder in terms of expertise on a specific topic, see my discussion at the link here.Invoking Multiple Expert PersonasWe are now then ready to combine the notion of personas, expertise, and the idea of using multiple instances.If you invoke just one persona, lets say it is an expert in climate science, there is a strong chance that the generative AI will give a particular bent to that persona. It might be that the persona is mainly shaped around the atmospheric and weather facets of climate science. Thats fine, except that you could end up getting responses that are confined to that arena. The persona might skip considering other areas such as the economics of climate science.Aha, this brings us to the notion of invoking multiple expert personas, all at once.You can pretend that a room full of experts is being convened. The instructions to the AI are that multiple expert personas are to be defined and used simultaneously. You can either let the AI choose what those personas will consist of, or you can shape the direction of each persona. This depends on what you are trying to accomplish with the simulation.I will next walk you through some examples to highlight the tradeoffs of how this is accomplished.Getting Underway With Multiple Expert PersonasI went ahead and logged into ChatGPT by OpenAI to come up with an example for you. You might find it of keen interest that ChatGPT garners a whopping 300 million weekly active users. That is a staggering amount of usage.I briefly conducted an additional cursory analysis via other major generative AI apps, such as Anthropic Claude, Google Gemini, Microsoft Copilot, and Meta Llama, and found their answers to be about the same as that of ChatGPT. Ill focus on ChatGPT but note that the other AI apps generated roughly similar responses.Lets get underway.My entered prompt: I want you to pretend to be multiple experts. I will tell you what field of expertise they have. I will also tell you how many experts there are. Your job will be to then answer my associated questions by pretending to be those experts. Do you understand these instructions?Generative AI response: Yes, the instructions are very clear. I will wait for you to tell me what the field of expertise is, and how many experts there are to be involved. I will then answer your question based on those personas. Let me know when you are ready to proceed.Take a close look at the prompt that I entered.You can see how simple it is to get multiple personas on the table. I laid out for the AI that I want the AI to pretend to be multiple experts and that I will say what the area of expertise is. Furthermore, I clarified that the purpose for doing this is so that I can ask questions of the simulated experts and get (hopefully) suitably informed responses accordingly.That is a handy-dandy templated way to get the matter underway and you are welcome to use that same prompt in your endeavors.Taking The Experts For A Test DriveLets try out the multiple experts by stipulating a field of interest. I went with climate science for this example. In addition, I will pose a pressing question for the experts.My entered prompt: I want you to pretend to be three experts in the field of climate science. My question is this: What is the most pressing issue caused by climate change?Generative AI response: To confirm your request, I will establish three personas that are experts in climate science. I will refer to them as: (1) Dr. Green, an ecologist specializing in biodiversity, (2) Dr. Blue, an atmospheric scientist focusing on weather patterns, and (3) Dr. Brown, an economist studying the impact of climate change on global markets. They are to answer the question from each expert's perspective about what the most pressing issue is caused by climate change. Should I proceed?You can see that I opted to explore the field of climate science.In this case, before I invoked the personas, I had in the past asked numerous questions about climate science and knew that the generative AI had done a semblance of pattern-matching on climate science topics when it was initially data-trained. Im not suggesting that the AI is truly an expert and only mentioning that I did some pre-work to make sure that at least a minimum amount of data was scanned and patterned on in general.Observe what the AI did in response to my request.I had stated that I wanted three expert personas in climate science. Sure enough, the AI echoed to me that it would simulate three instances. I hadnt said what their specific detailed expertise might each be. The AI opted to go with three experts, each having a different subspeciality, consisting of an ecologist, an atmospheric scientist, and an economist.If I didnt want the personas to be on those subtopics, I could easily enter another prompt and tell the AI that the expertise choices should be changed. The AI helpfully opted to give names to the three expert personas (Dr. Green, Dr. Blue, Dr. Brown), making it easier for me to refer to each one specifically (the naming seems reminiscent of the now-classic movie Reservoir Dogs if you know what I mean).Getting An Answer From The Expert PersonasI will go ahead with the three expert personas and let the AI derive an answer to my posed question.Here we go.My entered prompt: Yes, please proceed, but be brief in their respective responses.Generative AI response: According to Dr. Green (ecologist), the most pressing issue caused by climate change is the rapid loss of biodiversity. Dr. Blue (atmospheric scientist) indicates that the most urgent issue is the intensification of extreme weather events. Meanwhile, Dr. Brown (economist) says that the biggest concern is the economic fallout of climate change. Would you like me to expand on any of those views?My entered prompt: Provide more detail by Dr. Brown on the economic ramifications.Generative AI response: Dr. Brown indicates that disruptions to agriculture, increased costs of disaster recovery, and forced migration due to rising sea levels will strain global markets. Developing nations are disproportionately affected, as they often lack the resources to adapt, leading to a widening wealth gap and global instability."I told the AI to be brief in the AI responses.It is up to you whether you want to get short answers or long answers. I usually prefer to start with short responses and then see whether the AI is on target. The problem with getting long answers at the get-go is that if you are paying for the use of AI, you might needlessly be racking up online costly processing cycles. I like to dip my toe in and then decide whether to go expansively.After getting a short answer from each of the three expert personas, as combined into one response, I decided to see what else Dr. Brown, the economist persona, might have to say on the topic. The AI responded accordingly.Big Question About Consolidating ExpertsOne of the toughest aspects of using multiple expert personas entails how to end up with a final answer. The simplest approach involves the AI merely stating what each expert persona had to say. This can be combined into one final response.For example, I asked to see a cohesive final answer.My entered prompt: I want you to combine the three answers into one cohesive final answer.Generative AI response: "The most pressing issue caused by climate change is its multifaceted impact. From an ecological standpoint, the rapid loss of biodiversity due to habitat destruction and shifting climates destabilizes ecosystems that provide essential services like pollination and carbon sequestration (Dr. Green). This ecological imbalance feeds into atmospheric challenges, as these weakened ecosystems struggle to regulate weather and climate, contributing to more frequent and severe extreme weather events such as hurricanes, floods, and droughts (Dr. Blue). Disrupted agricultural systems, soaring disaster recovery costs and forced migration amplify global inequality and strain financial resources, particularly in developing nations that lack the means to adapt effectively (Dr. Brown).The problem is that the presumed cohesive final answer by the AI is still disparate answers that happen to be lumped together.Without anthropomorphizing AI, lets shift gears and consider what happens with human experts. If you get human experts together and ask them to answer a tough question, the odds are they will each have a particular opinion. You wont necessarily get just one answer, unless the question at hand is something that lends itself to solely one answer, such as perhaps a numeric-oriented question that involves doing calculations and arriving at a single value.There is an entire body of literature on how to get human experts to coalesce toward one unified answer on a given topic. You can have them take a vote. They can be given metrics or boundaries that essentially force them into an agreed-upon answer. And so on.The same somewhat applies to the invoking of generative AI multiple expert personas, in the sense that youll need to tell the AI how it is to combine the disparate answers. You can take the route of specifically stipulating what the method should be. An easier approach is to force the AI to decide how to do so.In this case, as shown next, I went with a blending approach of allowing the AI to mix the expert personas responses as though the answer was derived from a single source.My entered prompt: You are still providing three separate recommendations. Try to blend them into one overall unified recommendation.Generative AI response: "The unified recommendation is to prioritize large-scale investments in nature-based solutions, such as reforestation, wetland restoration, and sustainable land management. These efforts address biodiversity loss by protecting habitats and fostering ecosystems that support life, while simultaneously mitigating extreme weather impacts by stabilizing climates and reducing the frequency and intensity of disasters. Additionally, such investments can drive economic growth by creating green jobs, enhancing agricultural productivity, and lowering the long-term costs of climate adaptation and recovery.Dealing With Generative AI MyopiaA disconcerting caveat of using generative AI to simulate multiple expert personas is that the AI is dipping into the same data set and pattern-matched data pool for each of the simulated personas.Heres why that raises the eyebrows. You probably assume that each persona is independent of the other ones. Unfortunately, thats not true. The AI is shaped around a large-scale data structure and is based on large-scale data training, all of which ends up as one gigantic pool. Each persona is a slice of that same pool. The gist is that the personas arent going to be independent, and they are bound to lean in similar directions. Any biases are likely to be carried into each of the personas.You can tell the AI to not allow any such bias to arise, but thats still problematic and you are going to get a likely false or misleading indication that the AI has abided by your request. There are prompting techniques that can help to try and somewhat soften the blow of those biases, see my description at the link here.A more compelling approach involves using more than one generative AI.The chances are that a different generative AI will have a different semblance of the pattern-matching and the data was used during the initial setup. As such, you are potentially going to get somewhat different answers. I say that this is only somewhat because most of the AI makers are nonetheless scanning much of the same parts of the Internet, see how this has led to a shared indication that has some disturbing consequences, per my discussion at the link here.Using Additional Generative AI AppsBased on the noteworthy qualms that my three expert personas are only within the confines of the one generative AI app that I was using, I opted to log into a different generative AI app and ask the same question that I had posed earlier.I then brought that answer into my underway online conversation with Dr. Green, Dr. Blue, and Dr. Brown, cheekily adding the answer as though it came from Dr. Purple.Heres what happened.My entered prompt: I went ahead and asked a different generative AI to provide one expert opinion or persona on the same topic. I will refer to this persona as Dr. Purple. Here is what the AI said: Focus on accelerating the transition to renewable energy systems, such as solar, wind, and geothermal power, while simultaneously phasing out fossil fuels. I want you to now include that fourth opinion and tell me how it impacts the three experts you are simulating.Generative AI response: The approach of Dr. Purple addresses biodiversity loss indirectly by reducing habitat destruction linked to fossil fuel extraction and mitigating carbon emissions that drive climate instability (Dr. Green). It curbs extreme weather events over time (Dr. Blue) by slowing the progression of global warming. Economically, it promotes energy security, reduces long-term energy costs, and creates millions of jobs in the clean energy sector (Dr. Brown). By targeting the root cause of climate changegreenhouse gas emissionsthis recommendation provides a scalable solution with long-term benefits for ecosystems, weather stability, and global economies. This perspective shifts focus to energy systems, providing an actionable and complementary strategy to the previous recommendations.You can see that the generative AI sought to intertwine the answers of all four expert personas.Having Many Experts Has Its Ups And DownsCongratulations, you are now ready to try out the use of multiple expert personas.Id suggest that you pick a topic that you know something about and start with that as your means of experimenting with multiple expert personas. This allows you to readily gauge whether the responses are making sense. It will prepare you for coping with subject areas that you arent familiar with and when opting to involve multiple expert personas.During my classes on prompt engineering, I place the use of multiple expert personas into the advanced portion of the course. The technique is something you wont necessarily use constantly. The aim would typically be when you are examining a topic that youve not previously considered and for which you find useful seeing multiple perspectives. One venue in which this approach especially shines is in an educational setting, such as having multiple experts debate a legal issue such as a portion of the constitution. It is almost like having a crew of legal beagles pontificating on a piece of the law.Ill close this discussion on multiple expert personas with a few enlightening quotes from some experts.Franklin D. Roosevelt famously said this: There are as many opinions as there are experts. This pertains to a comment that I mentioned earlier. Unless the question posed has a singular final answer, the likelihood is that your multiple expert personas are going to provide a multitude of viewpoints and not especially land on a single end-all response. Please keep that in mind.Finally, the great Thomas Jefferson made this illuminating remark: Difference of opinion leads to inquiry and inquiry to the truth. May your use of generative AI entail abundant and probing inquiries, and may those inquiries, in turn, lead to the truth.Thats mindful sage advice in this modern-day era of advanced AI.

The EA app is our fastest and lightest PC client to date. With the new streamlined design you will easily find the games and content you're looking for and discover your new favorite games. With automatic game downloads and background updates you can ensure that your games are ready to play when you are.Build your ultimate friends list by connecting your EA account to other platforms and services like Steam, Xbox and PlayStation. You'll be easily recognizable with your custom unique ID. Once you're connected, know what and when your friends are playing so you can jump in and play together.For our Origin players, we've worked hard to make the transition to the EA app as simple as possible. We will be inviting you to make the move soon, and by the time you receive your invite, all your games and content, including games previously installed, will be ready and waiting for you on the EA app. Your local and cloud saves will transfer forward ensuring you can pick up where you left off. Your friends list transfers, too, so you won't have to worry about remembering all those player IDs.The EA app is now available for supported Windows PCs. MacOS players - Origin for Mac continues to be the place you can access your games.FeaturesDesigned for speedThe fast, optimized platform makes it easier than ever to discover, download, and play. So jumping into your game takes less time and fewer clicks.Built to connectLink your EA Account with your favorite gaming platforms to import friends lists and play together.Discovery at your fingertipsSee what your friends are playing, find EA's newest releases, and add them to your collection within a few clicks.Discover new games & play old favoritesExplore a huge, evolving library of titles ranging from indie darlings to triple-A hits.What's NewSignificantly improved My Collection loading speed, particularly for larger libraries. Everything started moving much more quickly once we switched over from the Dewey decimal system.Game Hub background videos can now be paused. From your Settings, you can choose to play or pause background videos automatically when visiting a Game Hub. Or you can pause background videos manually, whatever you like.Updated the main navigation to improve discoverability of the Home and Browse pages. The main navigation needed an overhaul because, before that, we just had to hand out maps and a compass, and hope for the best.Crash fixes for edge cases when launching games, launching the application, and exiting the application. Some of the feuding plants and zombies got a little carried away during battle and brought the fight into the app's framework, but we were able to detangle the roots and cart off the undead without any casualties.Other bug fixes and improvements.

Table of ContentsTable of ContentsActivating Apple Intelligence and GeminiGemini vs Apple Intelligence: how theyre similarKey differences between Gemini and Apple IntelligenceUnderneath: Gemini Advanced vs ChatGPTOne more thing: where Apple Intelligence gets it so rightWhich do I prefer: Gemini or Apple Intelligence?If youre looking for the best AI experience on a phone, chances are two different AI makers come to mind. For the iPhone 16, Apple Intelligence is the answer, while for Pixel 9 series and the best Android phones its Googles Gemini. Of course, you can also download Gemini as a standalone app on the iPhone, but Apple Intelligence is the default AI option.Both companies offer a range of nearly identical features, at least in what they promise to offer, but there are also nuanced differences. Google Gemini is mostly focused on using AI to help you create, edit, and generate content. In contrast, Apple Intelligence focuses more on personal use cases and integration across a range of apps.Recommended VideosIve been using both Gemini and Apple Intelligence for months and both AI services have their pros and cons. After testing both for months, heres what Ive found.RelatedGemini Advanced on the Google Pixel 9 Pro Fold. Andy Boxall / Digital TrendsActivating either AI platform is fairly intuitive, especially if youve used an Android phone or an iPhone before. Gemini replaces Google Assistant as the default assistant on your phone, although you can disable this which you may want to do, especially if you rely on Google Assistant for your smart home. Gemini can be activated most commonly with a swipe from the bottom corner of the screen, although its also available via the Hey Google hot word.Similarly, Apple Intelligence is baked into the revamped Siri which can be activated using the Hey Siri codeword or by double pressing the power button. When you activate the new Siri, youll get a rainbow-style lighting effect around the edge of the entire display, instead of Siri taking over the entire display as it did in the previous generation.Andy Boxall / Digital TrendsBoth are simple to activate and use, so this ones a tie. I do think that Gemini is simpler to use and activate, especially as there are multiple ways to activate it, but conversely, the activation method can change between different Android phones.Using Gemini AI on the Google Pixel 9. Andy Boxall / Digital TrendsBoth platforms focus on using AI for three specific purposes: generative features such as creating and editing images or text as well as productivity features and a voice assistant. The former is the key focus for most AI makers but Ive often found that generative AI features can be somewhat of a gimmick. Yes, theyll create great memes, but they likely wont change your life.Both platforms allow you to edit images youve already captured to remove unwanted objects. Google has had this built into Magic Editor in Google Photos for several years, while iOS 18 natively brings this feature to the iPhone for the first time in the redesigned Apple Photos app.Take this image a friend took of me the morning after an intense night out. I asked both phones to remove the menu on the table and the results are fairly interesting.1. Original2. Apple Intelligence3. Google GeminiFirst, its immediately obvious that Apple Intelligence isnt as good as Gemini, as you can see the wood grain in the tabletop is angled in the same direction as the menu. That aside, Apple Intelligence does a great job at filling in the grains and ensuring that theres continuity in the before and after of the same photo.What about Google Gemini? Heres where Googles longer history comes into effect: its better by a considerable amount. First, it generates four different images for you to choose from. Second, it has more precision in allowing you to refine your selection before making an edit. However, at the same time, it takes more taps to get to the Magic Editor, and unless theyve used Google Photos in the past, an average person will probably find Apple Photos more intuitive.An iPhone showing an Apple Intelligence rendering of Steve Jobs in the Image Playground app. Jesse Hollington / Digital TrendsGoogles focus with Gemini is mostly on generative features, as well as making it a replacement for Google Assistant. It achieves the former extremely well, whilst it still needs some work as a true replacement for Google Assistant, especially if you need it for smart home controls.Gemini comes with a range of features that I enjoy using, especially Circle to Search, which debuted last year on the Galaxy S24 series and makes it effortless to search related to something on your display. Want to know where to buy shoes that you just saw on Instagram? Circle to search can look that up in seconds.Circle to Search with Save to Screenshots option on Google Pixel 9 Pro. Christine Romero-Chan / Digital TrendsMeanwhile, Apple Intelligence takes a different approach. It features many of the same generative features except for a true Circle to Search replacement but it is also made to be your assistant. Whichever app youre using, Apple Intelligence can edit, rewrite, or summarize text for you, which makes it particularly poignant when you use a variety of apps.There is also one other key difference between them: the models that they use.An iPhone prompting the user for ChatGPT approval. AppleIf you used Siri before the rollout of Apple Intelligence, youll know that it was not as good as Google Assistant; it wasnt even close. With that in mind, it almost always felt inevitable that Apple would turn to another provider for the underlying models that power Apple Intelligence.Google already pays Apple to be the default search engine on the iPhone something to the tune of almost $20 billion per year so its somewhat surprising that Apple turned to ChatGPT to provide the underlying models for Apple Intelligence.Using Gemini AI on the Google Pixel 9. Andy Boxall / Digital TrendsThis integration goes much further, and where the new Siri is unable to help, Apple has integrated ChatGPT as the default backup. This means there are some duplicate features you can generate images using Image Playground or ChatGPT and the same applies to some of the Writing Tools but it also means you have a vast array of information and data to work from. If you have a ChatGPT free or paid account, you can access even more features directly within Apple Intelligence.Comparatively, Google opts for a self-contained approach. The underlying model behind Gemini is Gemini Advanced, with Gemini 1.5 Pro in particular the current non-beta model. If you access Gemini via the web, you can also select the next-generation Gemini 2.0 model.Visual Intelligence on iPhones relies on the camera to make sense of the world around you. Christine Romero-Chan / Digital TrendsOne of the key differences between these two models is that Gemini 1.5 has a larger context window, while ChatGPT tends to be better at generating human-like text. Both apps allow you to build custom chatbots, but ChatGPT also offers more advanced features, and Plus or Enterprise users can create unlimited chatbots.One somewhat irritating thing about Apple Intelligence is that it doesnt use the latest GPT-4 model, which is far more advanced and capable. Its unclear whether Apple will roll this out at a later date, or itll be built into the next version of Apple Intelligence, but this is something Id like to see Apple integrate into Apple Intelligence. GPT-4 has a much fresher set of data to work with, which poses a challenge for the knowledge base that Apple Intelligence is working with.For example, I asked Apple Intelligence and Gemini who won the U.S. elections, and it generated an answer related to the 2020 election. After clarifying I meant the 2024 election, it gave me Google Search results. In this case, it was actually better than Gemini which wont discuss elections but this is an edge case and Gemini is regularly more accurate at recalling information than Apple Intelligence.Notification Summaries in Apple Intelligence on the iPhone 16 series Nirave Gondhia / Digital TrendsFor everything that Gemini is great for, theres one feature that Apple Intelligence gets right. In deciding how to make a useful AI, Apple focused on its ability to affect and improve your personal life, and Apple Intelligence is far better than Gemini at this.Ive already written that Notification Summaries are my favorite use of AI right now, but Apple Intelligence extends beyond that. Being able to call up Writing Tools to compose, refine, or edit text in any app is far better than Gemini which acts like an overlay to that app. Similarly, youll soon be able to recall information from any app, which should make the new Siri a far better personal assistant.iPhone 16 Pro (left) and Pixel 9 Pro Nirave Gondhia / Digital TrendsIve been using both platforms for months and answering this question is harder than I first expected. On the one hand, Google Gemini is a far better generative AI solution and has access to a much broader knowledge base than Apple Intelligence. On the other hand, Apple Intelligence is a much better personal assistant and has better integration with Apple devices.Then theres the long-term potential for each of these platforms. Google Gemini is the default AI provider underpinning the AI suite on most Android devices, while Apple Intelligence is focused solely on Apple devices but benefits from improvements made by ChatGPT (at least once its running the latest models).All things considered, Ive found that while Gemini is far more advanced than Apple Intelligence, its the latters focus on personal features that ensures I use it more often. When I want to search for something or edit a photo, I turn to Gemini, but for daily use, I find Apple Intelligence and in particular the Notification Summaries to be far more beneficial for daily life. That said, Gemini is undoubtedly the better AI platform, at least for now.Editors Recommendations

Ex-beachfront property? Field of mounds on Mars may be sign of erosion at the edge of an ocean What may have been an ancient shoreline has signs of a water-driven transformation. John Timmer Jan 20, 2025 5:14 pm | 0 The Mawrth Vallis region of Mars. Credit: NASA/JPL-Caltech/Univ. of Arizona The Mawrth Vallis region of Mars. Credit: NASA/JPL-Caltech/Univ. of Arizona Story textSizeSmallStandardLargeWidth *StandardWideLinksStandardOrange* Subscribers only Learn moreFor decades, we have been imaging the surface of Mars with ever-finer resolution, cataloging a huge range of features on its surface, studying their composition, and, in a few cases, dispatching rovers to make on-the-ground readings. But a catalog of what's present on Mars doesn't give us answers to what's often the key question: how did a given feature get there? In fact, even with all the data we have available, there are a number of major bits of Martian geography that have produced major academic arguments that have yet to be resolved.In Monday's issue of Nature Geoscience, a team of UK-based researchers tackle a big one: Mars' dichotomy, the somewhat nebulous boundary between its relatively elevated southern half, and the low basin that occupies its northern hemisphere, a feature that some have proposed also served as an ancient shoreline. The new work suggests that the edge of the dichotomy was eroded back by hundreds of kilometers during the time when an ocean might have occupied Mars' northern hemisphere.Close to the edgeTo view the Martian dichotomy, all you need to do is color-code a relief map of the Martian surface, something that NASA has conveniently done for us. Barring a couple of enormous basins, the entire southern hemisphere of the red planet is elevated by a kilometer or more, and sits atop a far thicker crust. With the exception of the volcanic Tharsis region the boundary between these two areas runs roughly along the equator. There's a clear difference between Mars' northern and southern hemispheres, called the Martian dichotomy. Credit: NASA There are two mysteries associated with this dichotomy. One is how it got there, with ideas that range from an abortive early form of plate-tectonics to various planet-shaping impact scenarios. The second is whether it served a function early in the planet's history. All indications are that Mars had a warmer, watery past, and there have been proposals that included an ocean filling Mars' northern basin. But that has also been subject to debate.The new work focuses on an area called Mawrth Vallis, which sits at the edge of the dichotomy. Relative to the northern basin, it's a kilometer-high plateau cut by a major outflow channel that seems to have been caused by one or more massive floods. The slopes surrounding the plateau feature different types of clay-derived minerals, suggesting the area had been subject to interactions between the original materials and water.Rather than focusing on the plateau itself, the work focuses on the neighboring lowlands, which include a large region dotted with thousands of buttes and mesas that rise roughly a kilometer above the surrounding plains. Using data from the ESA's Mars Express mission, they determine that these features tend to top out at the same height as the nearby plateau. And, using data from NASA's Mars Reconnaissance Orbiter, they determined that the clays present along the slopes match those found on the plateau as well.Their conclusion from this is that the mesas and buttes are the remains of what was once a far larger plateau, which was largely eroded away on the side facing the northern basin. And that erosion took place across a pretty significant distance, as the buttes extend hundreds of kilometers away from the present highlands.And, just as at the highland plateau, these mounds hint at a water-based process that modified the rocks from the top down. That's because the deeper clays are often magnesium-rich, which tends to happen when water comes in contact with volcanic rocks or material with similar chemistry. Closer to the surface, things transition to aluminum- and iron-rich clays. These clays can occur when the water source is acidic or can be simply due to longer exposure to water, as the magnesium clays are a bit more soluble.A shoreline transformed?The huge area covered by these mounds gives a sense of just how significant this erosion was. "The dichotomy boundary has receded several hundred kilometres," the researchers note. "Nearly all intervening materialapproximately 57,000cubic kilometers over an area of 284,000square kilometers west of Ares Vallis alonehas been removed, leaving only remnant mounds."Based on the distribution of the different clays, the team argues that their water-driven formation took place before the erosion of the material. This would indicate that water-rock interactions were going on over a very wide region early in the history of Mars, which likely required an extensive hydrological cycle on the red planet. As the researchers note, a nearby ocean would have improved the chances of exposing this region to water, but the exposure could also have been due to processes like melting at the base of an ice cap.Complicating matters further, many of the mounds top out below one proposed shoreline of the northern ocean and above a second. It's possible that a receding ocean could have contributed to their erosion. But, at the same time, some of the features of a proposed shoreline now appear to have been caused by the general erosion of the original plateau, and may not be associated with an ocean at all.Overall, the new results provide mixed evidence for the presence of a Martian ocean. They clearly show an active water cycle and erosion on a massive scale, which are both consistent with having a lot of water around. At the same time, however, the water exposure the mesas and buttes have experienced needn't have come through their being submerged by said ocean and, given their elevation, might best be explained through some other process.Nature Geoscience, 2019. DOI: 10.1038/s41561-024-01634-8 (About DOIs).John TimmerSenior Science EditorJohn TimmerSenior Science Editor John is Ars Technica's science editor. He has a Bachelor of Arts in Biochemistry from Columbia University, and a Ph.D. in Molecular and Cell Biology from the University of California, Berkeley. When physically separated from his keyboard, he tends to seek out a bicycle, or a scenic location for communing with his hiking boots. 0 Comments

HealthResearch is revealing the complex relationship between sleep and the gut microbiome, raising the prospect that eating better during the day might help you get a better nights rest 20 January 2025 Foxys_forest_manufacture/Getty ImagesThere are many things we can blame for a bad nights sleep screen time, stress, too much booze. Now there is another culprit: the microbes in our gut.This article is part of special series investigating key questions about sleep. Read more here.We have long known that our microbiome has a powerful influence on our health, and new research is revealing that this extends to our sleep, too. But it is a complex, two-way relationship. The microbiome is influencing sleep, and sleep is influencing the microbiome, says Elizabeth Holzhausen at the University of Colorado Boulder. The good news is that there are ways we can intervene.At first glance, the link between your stomach and sleeping patterns might not be obvious, but a growing number of studies are shedding light on the impact they have on each other. For instance, a 2023 study of 720 people found that diversity of microbes in the gut was associated with better sleep. Likewise, a look at nearly 1000 people by researchers at Kings College London (KCL) and other institutions, in association with the personalised nutrition company Zoe, found that irregular sleep patterns were linked to a boost in the number of unfavourable bacterial species associated with poorer health outcomes.Whats more, changes in the composition of the gut microbiome are associated with several sleep conditions. Rapid eye movement sleep behaviour disorder, for instance, which causes sleepers to physically act out their dreams during REM sleep, is linked to a depletion of gut bacteria that produce the short-chain fatty acid butyrate and a rise in bacteria that increase inflammation.

Ahead of the swearing-in ceremony, the Bidens greeted the Trumps on the North Portico of the White House.Joe Biden and Jill Biden welcomed Donald Trump and Melania Trump. Rod Lamkey, Jr./AP Former Vice President Kamala Harris and former second gentleman Doug Emhoff also greeted Vice President JD Vance and second lady Usha Vance.Kamala Harris and Doug Emhoff greeted JD Vance and Usha Vance. Alex Brandon/AP Attendees took their seats in the Capitol Rotunda, where the inauguration was held due to freezing temperatures.The Capitol Rotunda. ANDREW HARNIK/POOL/AFP via Getty Images Tech billionaires, including Mark Zuckerberg, Jeff Bezos, Sundar Pichai, and Elon Musk, were seated on the inaugural platform.Mark Zuckerberg, Lauren Sanchez, Jeff Bezos, Sundar Pichai, and Elon Musk at Donald Trump's inauguration. Julia Demaree Nikhinson - Pool/Getty Images Former Presidents Bill Clinton, George W. Bush, and Barack Obama took their seats in the Rotunda.Bill Clinton, Hillary Clinton, George Bush, Laura Bush, and Barack Obama at Donald Trump's inauguration. Chip Somodevilla/Getty Images Vice President JD Vance was the first to be sworn in.JD Vance. Saul Loeb/Pool photo via AP President Donald Trump took the oath of office at noon as per tradition.Donald Trump. Saul Loeb/Pool/AFP via Getty Images "The golden age of America begins right now," Trump said in his inaugural address, which included numerous policy proposals.Donald Trump's inaugural address. Kevin Lamarque - Pool/Getty Images After Trump's address, Carrie Underwood sang "America the Beautiful."Carrie Underwood. Chip Somodevilla/Getty Images The Bidens departed the Capitol on Marine One, completing the peaceful transfer of power.Marine One leaving the Capitol. ANDREW CABALLERO-REYNOLDS/AFP via Getty Images

When it comes to speeches, there are two Donald Trumps. The first is Teleprompter Trump, who reads a prepared speech and tends to be staid, sleepy, and insincere. The second is Rally Trump, who riffs in front of a cheering crowd and is wild, aggressive, and more true to the person that Trump really is.We saw this duality on display immediately after Trumps inauguration. In his official inaugural address in the Capitol Rotunda, Teleprompter Trump delivered a largely unmemorable performance a sleepy address that gave audiences little substance to remember it by. In an impromptu follow-up performance given to the overflow crowd in nearby Emancipation Hall, Rally Trump made an appearance giving a rambling but undeniably more energetic monologue that Trump himself described as a better speech than the one I made upstairs.Rally Trumps speech was a much better guide to what actually animates Trump than the more buttoned-down teleprompter address. And the portrait the second address painted is of a man who remains convinced of his own fictions and obsessed with revenge against those who challenged them.The Rally Trump speech really got going when Trump began talking about things he left out of the official inaugural address. He singles out prospective pardons for January 6, 2021, Capitol rioters as an important example, saying its action not words that count and youre gonna see a lot of action on the J6 hostages.You can see how deeply Trump cares about transforming the official history of January 6. Its not good enough that he is returning to office: He needs to rewrite what happened such that the people who rioted to try and steal the 2020 election for him are the victims hostages rather than criminals. Its all in service of the grander goal of insisting that Mr. Trump cannot lose and never has, and of using his new powers to try and force reality to match this insistence.Similar thinking was at work in Trumps next riff on outgoing President Bidens preemptive pardons for potential Trump prosecution targets like General Mark Milley, Liz Cheney, and Bidens own family members.Trump insisted these people were very, very guilty of very, very bad crimes, accusing the January 6 committee which he referred to as the unselect committee of political thugs of deleting all the information on Nancy Pelosi (its unclear what criminal statute this would fall under). Its clear that Trump really does want to go after these people as part of his campaign to rewrite the events of the 2020 election; the extent to which hes stymied by Bidens pardons remains an open question.Over the course of the next half hour, Trump continued down his revisionist lane.Trump implied that Liz Cheney opposed him not because of any perceived threat to democracy but because her dad was a war profiteer. He spent a while disputing a specific piece of January 6 testimony that he attempted to seize the wheel of the presidential limousine to drive to the Capitol. He explicitly restated that the 2020 election was rigged against him, and then insisted that we would have won the state of California in 2024 if it werent for illegal votes.The point is not that any of this is new ground for Trump. Rather, its that none of it is.In his first truly authentic speech after returning to office, where he felt unchained to discuss what he really cared about, he spent the bulk of the time obsessing over election results and January 6, endlessly litigating the past and (at times openly) stating his desire to seek recompense and revenge for the indignity of losing an election.The Rally Trump speech was the truest reflection of the once-and-current presidents feelings and, I suspect, his governing priorities. And four years of a president who uses his power to punish political enemies and reward his lawbreaking friends does not augur well for American democracy.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: Politics

New dinosaur horror game skips PC version because of vulgar modsMichael BeckwithPublished January 20, 2025 5:09pmUpdated January 20, 2025 5:09pm Therell be no Xbox version either but thats due to lack of time and resources (TeamKill)Despite using PC footage in its announcement trailer, a new dinosaur horror game will end up being exclusive to the PlayStation 5.With Capcoms Dino Crisis series still MIA, and no sign of a release date for Jurassic Park: Survival, hopefully the newly announced Code Violet from American studio TeamKill Media can satisfy our need for dinosaur gaming action.Its already slated for a July launch this year and while it looks to be taking itself more seriously than Capcoms agreeably cheesy Exoprimal, it at least promises a shootout against a T-Rex.Code Violet is so far only coming to PlayStation 5, but even though the trailer uses footage captured on PC the developer has ruled out a dedicated PC version because it doesnt want people modding the game.TeamKill pins the blame on sexual mods, presumably referring to mods that render characters in skimpier clothes or sometimes none at all.We do not want anyone modding vulgar versions of the main character as well as other characters in the game, reads a scathing post from TeamKills X account.It adds that such mods would destroy their artistic vision, and Making a joke out of our art and possibly tarnishing the reputation of our voice actresses and actors is not worth the extra money we can make.While that seems a rather strange thing to say, TeamKill is the only studio out there to oppose the idea of modding, especially when it comes to inappropriate extra.In 2021, the talent agency for Japanese actor Takuya Kimura prevented Sega from porting the Judgment games to PC (per Kotaku). This was because the agency wanted to protect Kimuras likeness, which is used for the main character.Kimura is a massive star in Japan, so the possibility of his Judgment character model being altered by fans may have spooked his agency. Although an agreement was clearly reached since PC ports for both games eventually arrived.Elsewhere, companies like Square Enix have explicitly asked that modders dont make anything inappropriate for their games, while others like Capcom have gone so far as to have them removed. The sillier mods are often left alone (NexusMods/Capcom)Even when actual human likenesses arent involved, nude mods can earn game companies the wrong kind of attention. One infamous example from 2023 saw the hosts of a livestreamed Street Fighter 6 tournament accidentally leave a nude Chun-Li mod on (via Kotaku).Capcom never formally commented on the matter, but a video it posted on anti-cheat and anti-piracy measures in PC games several months later said that certain mods are offensive to public order and morals and can be detrimental to the company. Both in terms of reputational damage and in terms of workload.Most recently, multiplayer shooter Marvel Rivals became a hotbed of custom-made character skins and while some simply swapped non-Marvel characters into the game, there was no shortage of nude skins either.More TrendingSo, it shouldnt have been too surprising that the games season one update saw any and all mods disabled. Developer and publisher NetEase Games told IGN: It is not recommended to modify any game files, as doing so carries the risk of getting banned.In the wake of this, character artist Del Walker, whos previously worked for studios like Respawn and Naughty Dog, said in an X post there are a number of reasons why mods for live service games tend to be banned.Aside from NSFW mods potentially harming a studios reputation and artistic vision, Walker pointed out that if players can get custom skins for free, theyd feel less inclined to spend money on the official skins: Studios aint about to let you mess with their income.There are some studios that actively support the modding scene. Bethesda and Larian Studios have introduced tools to allow for more complex mods though theyre incresing the exception rather than the rule. Unsurprisingly, Marvel Rivals modders have already found a workaround (NetEase)Emailgamecentral@metro.co.uk, leave a comment below,follow us on Twitter, andsign-up to our newsletter.To submit Inbox letters and Readers Features more easily, without the need to send an email, just use ourSubmit Stuff page here.For more stories like this,check our Gaming page.GameCentralSign up for exclusive analysis, latest releases, and bonus community content.This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply. Your information will be used in line with our Privacy Policy

Altadena, California was the home of the esteemed Afrofuturism pioneer who wrote Parable of the Sower.

Petapa Market Renovation / Taller MRD + DF ArquitectosSave this picture! Jess Omar Luis SalvatierraMarketSanta Mara Petapa, MexicoArchitects: DF Arquitectos, Taller MRDAreaArea of this architecture projectArea:4650 mYearCompletion year of this architecture project Year: 2023 PhotographsPhotographs:Jess Omar Luis SalvatierraMore SpecsLess SpecsSave this picture!Text description provided by the architects. What we found on the site was a publicly fractured urban and social space, with a very rich program established by the PMU led by SEDATU, which began the unification and integration. Among the pre-existing elements related to the cultural character of the site, there was a public market completely affected by the earthquake of 2017, a church of high heritage value with a strong sense of belonging and beauty that has recently been restored, both prominently featuring brick and clay in ochre tones.Save this picture!An integral layout of the entire block was projected in such a way that through its gestures and intentions; represented with enclosures, pavements, landscaping, plazas, retaining walls, pergolas among other elements, the mentioned program will be unified. We started with the restoration of the market, a project that preserves its origins and forges its legacy with clay tile roofs, wooden beams, and pitched roofs.Save this picture!Save this picture!Taking this construction as a starting point, a pattern emerges to continue the sloped roofs in the sports court and multi-purpose covered plaza that propose a human and urban scale for the municipality and for pedestrians. An open plaza continues that, through a circular esplanade, crosses the roadway, dialogues, and connects with the church, generating a personal link and reducing the importance of the roadway.Save this picture!It concludes with the last section, which is the preschool, which maintains the pattern of the same orthogonal structure and its exposed framework. It is a single-story building whose rooftop is utilized, framing the impressive view of the mountains. It was built with concrete and apparent ochre-colored prefabricated elements, bricks, and clay tiles in the same tones. Cleanliness, order, scale, and respect for its context predominate.Save this picture!Project gallerySee allShow lessProject locationAddress:Santa Mara Petapa, MexicoLocation to be used only as a reference. It could indicate city/country but not exact address.About this officeDF ArquitectosOfficePublished on January 20, 2025Cite: "Petapa Market Renovation / Taller MRD + DF Arquitectos" [Renovacin del mercado Petapa / Taller MRD + DF Arquitectos] 20 Jan 2025. ArchDaily. Accessed . <https://www.archdaily.com/1025916/petapa-market-renovation-taller-mrd-plus-df-arquitectos&gt ISSN 0719-8884Save!ArchDaily?You've started following your first account!Did you know?You'll now receive updates based on what you follow! Personalize your stream and start following your favorite authors, offices and users.Go to my stream