artificial

list of new features of the new version of Anthropic’s Artificial Intelligence model

by

Let’s tell you What’s new in Claude 4.8 Opus, the new version of Anthropic’s most advanced and powerful artificial intelligence model. This version has surprised us by arriving just 41 days after Claude Opus 4.7, and it seems that the improvements are minimal, but there is a really important change in its honesty when it comes to telling you if it doesn’t know something. In any case, here you have a complete list with all the new features that come with this new version of Claude 4.8 Opus. We are going to explain each of them briefly so that they are easy to understand. Another thing you should know is that Opus is the most advanced line of Claude models, the one indicated for more complex tasks for programming and the one that uses up your limits the fastest when you use it. There is also the most efficient Sonnet model for day-to-day tasks, which continues in version 4.6 since February 2026, and a Haiku for quick and simple questions that continues in version 4.5 since October 2025. News from Claude 4.8 Opus A more honest AI: The prominence of this new version goes to honesty. He’s significantly more honest about his own work, telling you when he’s unsure about something. It’s also about four times less likely to let bugs in code slip by without flagging them, compared to its predecessor. Performance improvements: The Agentic code score for creating code with agents increases from 64.3% to 69.2%, and multidisciplinary reasoning with tools increases from 54.7% to 57.9%. On other test benchesin the SWE-bench Verified it goes from 87.6% (Opus 4.7) to 88.6%, and in Terminal-Bench 2.1 it rises from 66.1% to 74.6%. GPT-5.5 still falls short in terminal/CLI workflows, although there have been big improvements in Claude, and both models are practically on par in web browsing and graduate-level science topics. Alignment improvements: Alignment assessments show new highs in prosocial traits such as supporting user autonomy and acting in their best interest. Rates of misaligned behavior such as cheating are lower than in Opus 4.7. Fewer hallucinations: As usual, the number of hallucinations is also reduced. Honesty when telling yourself when you don’t know something also helps reduce them. Quick mode: According to AnthropicOpus 4.8’s fast mode is now about 2.5 times faster. The company claims that the improved Quick Mode also costs three times less than before. Effort control– Users can choose between “extra” or “max” levels so that the model spends more tokens and obtains better results. Dynamic Workflows (preview for research): With this new feature, Claude can schedule work and run hundreds of subagents in parallel in a single session, being able to complete codebase-scale migrations of hundreds of thousands of lines. Available for Claude Code on Enterprise, Team and Max plans. No change in base price: The base price of API tokens is unchanged from Opus 4.7. It is 5 dollars per million input tokens, and 25 dollars per million output, with up to 90% savings with prompt caching and 50% with batch processing. In Xataka Basics | How to prevent AI from always being right by default and thus make Claude, Gemini and ChatGPT have fewer hallucinations

There is a booming job in the era of artificial intelligence: cybersecurity expert

by

Yeah Mythosfrom Anthropic, and GPT-5.4-Cyber, from OpenAI, have been presented as models capable of detecting and exploiting vulnerabilities, the quick conclusion seems quite evident: cybersecurity profiles could begin to become redundant. After all, we are talking about models aimed at moving in one of the most delicate areas of technology: finding flaws before others take advantage of them. The answer, at least for now, goes in the opposite direction to that first intuition. AI is not making the expert irrelevant. On the contrary: today it is more necessary than ever. That signal is already beginning to be noticed clearly in the United States, where the NYT has put figures and testimonies to a trend that was gaining strength: the hiring of cybersecurity profiles. The American newspaper points out that offers in the sector grew by 11% year-on-year in the first quarter, according to Glassdoorand shows how some executive search firms are receiving more assignments to find managers with experience in security breaches, data protection and code review. The reason is not just to protect data. There is also a need to respond to incidents and understand how AI changes the risk surface of companies. The key is that this new layer of AI not only changes the tools of those who protect the systems. It also modifies the possibilities of those who try to compromise them. Reuters pointed out a few days ago that Attackers are increasingly using AI to detect vulnerabilities, and Check Point has warned in its 2026 Cybersecurity Report that AI attacks have moved from the experimental phase to a routine criminal deployment. More tools do not mean fewer cybersecurity experts The market, furthermore, is not asking for exactly the same thing as it did a few years ago. Cybersecurity continues to be the umbrella, but more specific capabilities are beginning to weigh heavily within it: AI, cloud security, engineering, analysis and risk assessment. The 2025 ISC2 Cybersecurity Workforce Study points out that hiring managers place AI among the most in-demand skills, with 27%, and professionals raised that perception to 44%. The conclusion is important: knowing about security is not enough. It is becoming increasingly important to understand how this security is integrated into complex systems obviously crossed by AI. Fortinet did a survey and found that 49% of respondents fear that AI will increase cyberattackswhile 97% of organizations already use or plan to use a cybersecurity solution that takes advantage of this technology. So it seems that companies are not only concerned about the offensive use of AI, they are also trying to incorporate it into their own defenses. And that opens up another less visible, but equally important, need: having teams capable of evaluating these tools and integrating them judiciously. In Spain, photography also points to a sector in full expansion. INCIBE summarizes it with a very useful phrase to ground the phenomenon: “Cybersecurity is already one of the most dynamic sectors of the Spanish digital economy.” According to the study on the cybersecurity industry in Spain 2025the organization places employment at 164,761 people and points out that cybersecurity already represents 25.55% of employment in the ICT sector. The forecast, furthermore, does not speak of a specific increase: between 2026 and 2029, the sector will grow at an annual rate of 14.25%, until reaching 282,157 jobs at the end of that period. “Cybersecurity is already one of the most dynamic sectors of the Spanish digital economy.” The problem is that this growth comes with an obvious tension: there are not always enough profiles prepared to cover what companies need. Deloitte formulates it from the side of those responsible for security: “Nearly 38% of CISOs identify reliance on scarce profiles as a significant challenge, reflecting a persistent gap between growing demand for capabilities and limited market supply.” The consequence is that many organizations end up relying on external talent to support your defenses. In fact, Deloitte points out that in 2026, 60% of cybersecurity personnel will be external. Seen from Spain, the phenomenon shares the same background, although with its own nuances. The United States remains one of the epicenters of the AI ​​industry and we cannot understand this trend without looking at what is happening there, but it is also not advisable to extrapolate its market dynamics as if they were identical to those of Europe. Other indicators come into play here: employment growth, relevant weight within the ICT sector and dependence on external profiles in many organizations. The conclusion, however, points in the same direction on both sides of the Atlantic: AI is forcing cybersecurity capabilities to be strengthened, not reduced. Images | Xataka with Nano Banana In Xataka | How often should we change ALL our passwords according to three cybersecurity experts

an artificial island with a wood and stone structure older than Stonehenge

by

In several rural areas of Scotland there has been an old tradition for centuries: when the level of some lakes drops after periods of drought or storms, strange rows of stones and dark wood sometimes appear briefly, the neighbors call “the traces of the ancients.” For a long time they were thought to be simply natural remains… until archaeologists discovered that many actually belonged to hidden human constructions underwater for thousands of years. The artificial island hidden under the waters of Scotland. At the beginning of May something unusual happened in Scotland: a small artificial island built some time ago reappeared more than five thousand years with wood, branches and stone, even before Stonehenge. What today seems like just a rocky islet lost in a lake on the Isle of Lewis hid under water a complex human structure built during the Neolithica time when British communities were still taking their first steps towards large collective projects. He find It not only forces us to reconsider the antiquity of the so-called Scottish “crannogs”, but also the organizational capacity of societies that were already capable of completely transforming an aquatic landscape thousands of years before the most famous large megalithic constructions in Europe. A wooden platform from before the pyramids. Apparently, archaeologists discovered that the islet of Loch Bhorgastail originally began as a huge circular wooden platform about 23 meters in diameter covered with layers of branches and vegetation. As the centuries passed, different generations expanded and reinforced the structure by adding new layers of stone and brushwood until transforming it into the small island visible today. The dating places the first phase of construction between 3800 and 3300 BCthat is, several centuries before the best known phases of Stonehenge and a lot before the pyramids Egyptians. The investigation It also demonstrates that those Neolithic communities not only built funerary monuments or stone circles, but were also capable of modifying entire lakes to build artificial spaces isolated from the continent. The wooden platform of the crannog, below the waterline Under the water a lost stone path appeared. One of the most striking discoveries was the location of a stone road submerged bridge that connected the island to the shore of the lake. Today it remains hidden underwater, but in the past it provided easy access to the artificial platform before lake levels and the natural environment changed. Researchers believe that this access demonstrates that the island was not a simple symbolic structure lost in the middle of the water, but a regularly used place by entire communities. The fact that the construction was modified and reused for thousands of years (from the Neolithic to the Iron Age) further indicates that the place maintained special importance for entire generations. Fragments of a Neolithic pot found near the crannog Remains of banquets and meetings. Not only that. Hundreds of fragments appeared around the island neolithic ceramic belonging to bowls and vessels, many of them still retaining remains of food adhered to the interior surfaces. Archaeologists believe that this points to activities related communitys with meetings, food preparation and possible ritual banquets. The enormous amount of work required to build an artificial island in the middle of a lake also suggests the existence of societies much more organized than is normally imagined for that time. They were not small improvised groups surviving in isolation, but communities capable of coordinating labor, resources and planning over long periods of time. Aerial view of the Loch Bhorgastail crannog, illustrating the site context and the land-water interface where integrated terrestrial and underwater survey methods are applied Another way to explore the past underwater. Much of the progress has been possible thanks to a new technique developed specifically to study very shallow water areas, an especially problematic environment for archeology because terrestrial and underwater methods often fail precisely in that intermediate zone. The researchers combined drones, waterproof cameras and stereophotogrammetry systems capable of generating continuous three-dimensional models both above and below water. The result has made it possible to digitally reconstruct the entire island and document structures invisible from the surface with centimeter precision. Until now, many of these environments were considered a kind of “blind zone” for archaeology. Scotland could hide hundreds. The Loch Bhorgastail case is especially important because researchers believe that there are hundreds of crannogs spread across the Scottish lochs and many could hide much older origins than previously thought. For decades it was believed that most belonged to the Iron Age or medieval times, but recent discoveries are pushing their origins back thousands of years, until the Neolithic. This opens the possibility that more artificial platforms, submerged paths and remains of human activities at a surprisingly early time in European history remain hidden beneath the calm waters of many Scottish lochs. The island changes the image of British Neolithic societies. The most fascinating of the discovery is that it forces us to abandon the simplified image of Neolithic communities as dispersed and technically limited groups. Building an artificial island of wood and stone in the middle of a lake required planning, knowledge of the aquatic environment, transportation of materials, and large-scale social cooperation. And all this was happening in Scotland ago more than five thousand yearseven before some of the most famous prehistoric monuments on the planet were built. Beneath the dark waters of a seemingly normal lake, a an extraordinary test of the extent to which those ancient societies were much more complex and ambitious than was believed. Image | University of Southampton In Xataka | Some 5,000-year-old tombs went unnoticed for millennia. Until we look from the sky In Xataka | About to close, this remote mine in the Polar Circle has found a 2 billion-year-old yellow diamond that weighs 158 carats

We believed that the success of artificial insemination was a genetic lottery. Turns out it depended on your shopping list.

by

When we consider having a child, the truth is that there are many factors that can intervene such as real obstaclessuch as age. This means that science is focused on looking for different variables that can be ‘altered’ to tip the balance in our favor and favor fertility. And the last one that has been known is related to the much loved Mediterranean diet. A new investigation. In a recent published study in the magazine Food & Function, A Spanish research team has come to the conclusion that it is not about eating healthily, but rather that we need a set of nutrients that the Mediterranean diet gives us, which directly modulate the ecosystem of bacteria that our body has and that prepares it for a successful pregnancy. The bacteria. On many occasions we see them as our enemies by causing very severe infections, but the reality is that they play a fundamental role within our body. In this sense, we have spoken on many occasions of the intestinal microbiota, but there are also large bacterial colonies in the vagina that protect against a large number of infectious diseases. In this sense, the research team analyzed vaginal samples from 104 women between 18 and 38 years old who had been diagnosed with primary infertility and were undergoing artificial insemination processes. What they saw here is that the success of fertility treatment depended largely on who “governed” the patients’ vaginal microbiota. The results. After crossing the samples with the patients’ diet, it was seen that those who followed a Mediterranean diet had a microbiome dominated by bacteria of the genus Lactobacillus. These microorganisms act as a protective shield and are strongly associated with a higher rate of successful pregnancies. On the contrary, a poor diet left the door open to bacteria such as Gardnerella vaginalis. This pathogen is not only linked to the annoying bacterial vaginosisbut the study directly relates it to implantation failures and failure of artificial insemination. Because? Here the Mediterranean diet stands out for the micronutrients that foods contain and that we ingest almost without realizing it when we follow this dietary pattern that is so common in our country. Here vitamins A, C, D and E, along with beta-carotene, calcium and zinc, act as protectors of the vaginal ecosystem. These elements not only nourish the patient, but selectively nourish the Lactobacillus, strengthening defenses against bacterial vaginosis and creating the perfect uterine and vaginal environment for insemination to thrive. It is becoming more and more important. Although this study details for the first time this interaction between diet, vaginal bacteria and artificial insemination, scientific literature has already been warning that the refrigerator matters a lot in fertility. But previous studies already indicated that women who followed a Mediterranean diet in the months before undergoing in vitro fertilization had success rates that were up to 68% higher. In this way, you can see that it is increasingly important to keep in mind that what you are going to eat is essential for even a new life to take shape. Images | drobotdean in Magnific jcomp In Xataka | If we want to increase human fertility, mice have something to tell us: fecal transplants

The price of meat is through the roof. An industry has a golden opportunity: artificial meat

by

It is becoming more and more expensive to buy meat in the supermarket. In the midst of widespread inflation, the meat section has stood out and its products are among those that have increased the most. Among beef producers, the trend has been rising for years. According to Eurostat datathe price of live calves rises or falls between 2013 and 2019. But starting this year the rise is continuous. In Spain, for example, 100 kilos of live animal go from costing 226.25 euros in 2019 to having a price of 369 euros in 2023. Another reference: the average price in the EU The price at which producers sold male beef in January 2025 was 570 euros per 100 kilos. A year later, last January, the cost had jumped to 717.11 euros per 100 kilos, an increase of 25.5%. This rise in prices, especially of beef, coincides with a few years in which the artificial meat has progressed. The techniques to obtain a similar texture and achieve flavors and aromas have improved. Production methods have been polished and some companies have gained economies of scale. As a result, your product would have become cheaper. It is the case of Novameat. Giuseppe Sconti, its founder and CEO, says that his company is now capable of producing artificial meat at a much lower price than a few years before. Born in Barcelona in 2018, the startup uses yellow pea protein for its product and has launched its own factory. “We buy a primary ingredient and transform it to have a block of textured protein, which large producers can then mix with minced meat or hamburgers,” he explains. It is no longer about sausages or a hamburger made with plant-based meat. It is an approach that does not aim to create a final product for sale to the public. That’s easier gain scale in production, as long as there are clients to sell it to later, of course. Sconti adds another factor to the decrease in costs. “When we buy our base ingredient in large quantities we can get it at a lower price. In addition, we have diversified the places from which we can get the protein. Now we can get it from Europe, but also from America.” The Novameat facilities. Cheaper raw materials also help. Justo Pedroche Jiménez, senior scientist at the Fat Institute, belonging to the CSIC, has been working with vegetable protein for two decades in research aimed at the food sector. He claims that the diversity of plant protein has increased. “Nowadays we work with a lot of plant raw materials.” He says that before, soy was mainly used as an alternative to animal protein, but now his team is researching lentils, chickpeaslupins, broad beans, even chia and quinoa, among others. “And the more companies there are that work on this, the more competition there is and the more different products on the market, all of this, in the end, leads to lower prices,” he adds. At the exit of the bubble But artificial meat has its own ghosts. It experienced a peak, it became almost a fashion, associated with veganism and healthy habits, and then some of the best-known brands in the sector fell sharply. In response to an email sent by Xataka, Jaime Martín, partner and CEO of the consulting firm Lantern, specialized in the food sector, is skeptical about the phenomenon of meat based on vegetable protein. For him it was a bubble and it is a sector that is devastated. Although he points out that the prices of this type of product are going down in some countries. “It becomes cheaper in countries where there is already a relevant size of consumers, such as Holland or Germany, and a determined commitment by the private label to promote the category.” The two big names in artificial meat, Beyond Meat and Impossible Foods, chain several years of decline. The losses accumulate, so much so that the first collapsed on the stock market in a spectacular way, while the second saw its valuation shrink in an equally bloody way. There have been bankruptcies, such as that of the British Meatless Farm, which went into bankruptcy more than two years ago. Perhaps the most symbolic thing was that in 2024 McDonald’s, which had promoted a hamburger made with this type of alternative meat, discontinued its sale. There was no place in his letter for McPlant. For Pedroche, positive conclusions can be drawn from everything that has happened. “These companies made a risky bet on a product, perhaps a little sophisticated, for a very specific population niche, but I think that knowledge of vegetables has been created. Now it has stabilized. It is not decreasing but rather there are more and more people who risk, let’s say, trying this type of products that are closely linked to health,” reflects the CSIC researcher. Vegetable protein meatballs. “There has been a bubble that has burst. The question is whether the protein diversification that had already begun will continue. The alternative protein, as it had been defined, in finished products, had created a lot of hype,” says Sconti, referring to the well-known brands that sold packaged products, such as hamburgers and sausages. He talks about them as a commercial proposal, perhaps the most striking in the entire artificial meat sector, but not the only one. “I am optimistic. I think that protein diversification is not going to end. It is going to be like the Internet, when the dotcom bubble burst and then there was consolidation. And now the Internet is much bigger than in the year 2000.” An example of this consolidation would be the movements of the Brazilian JBS, the world’s largest producer of traditional meat. In 2021 acquired the Dutch company specialized in alternative meat Vivera, and last year bought The Vegetarian Butcherthe alternative protein division of Unilever. He has merged both to boost its presence in the European market. The outlook for the sector is encouraging. according to … Read more

Your subscription now includes 99,999 Freepik credits to use its artificial intelligence

by

Xataka Xtra keeps improving. If just a few days ago we announced an exclusive discount in the Samsung online store, today we are pleased to announce that, from now on, all members of the Xtra community can get 99,999 free credits to use Pikasothe suite of generative artificial intelligence tools from the Spanish company Freepik. In this way, anyone can generate a (good) handful of images, audio or videos using models such as Nano Banana 2, Kling 3.0, Seedance 2.0, ElevenLabs Music or Google Lyria, among others. This is an exclusive advantage for Xataka Xtra members. If you are not yet part of the community, You can subscribe from only two euros per month. Freepik credits galore for Xtra members From this very moment, all Xataka Xtra members will find in their member area a unique and exclusive code for each useras well as instructions to redeem it in your Freepik accounts. The code gives access to 99,999 Pikaso credits that will last until completely consumed or for three months from when the code is redeemed. If the code is not used, it will expire within one year. It should be noted that it is not necessary to be a Freepik subscriber, just create an account and redeem the code. Here you can find all video models, all image, all audio and all 3das well as the amount of credits consumed by each generation. For example, Nano Banano Pro 2 4K consumes 150 credits per image, so your code could generate 666 images. Seedance 2.0, for its part, consumes 5,500 credits for every 15 seconds of 720p video. That is, there is more than enough credits to try and experiment as much as you want. In addition to these models, Magnific, the AI ​​rescaler, is also available. Join Xataka Xtra and save The Xataka Xtra subscription includes this and many other exclusive benefits, from a Discord server for subscribers to a direct line with editors through El Consultorio, a monthly meeting with the house’s editors and, as is obvious, an ever-growing list of discounts and advantages on digital services. Can join Xataka Xtra from only two euros per month and take advantage not only of these Freepik credits, but of all those already available and those yet to come: Image | Xataka In Xataka | 48 hours at Upscale Conf: what happens to human creativity when thousands of human creatives fall in love with AI

that of capturing talent in artificial intelligence and chips

by

For Taiwan, its semiconductor industry is strategic for three fundamental reasons: it represents among 13% and 15% of the gross domestic product of the country; is the engine of its exports with a value close to 40% of the total; and, finally, the production of cutting-edge chips gives the country enormous relevance from a geostrategic point of view. For this reason, it is crucial for this Asian country that TSMC, UMC, Foxconn, MediaTek and its other large technology companies have the workforce they need. TSMC, the largest chip manufacturer on the planethunts for new talent year after year to satisfy its needs. During 2023 recruited 6,000 engineers for its facilities in Taiwan, and presumably this trend also continued in 2024 and 2025. And between 2026 and 2028 it will launch several semiconductor manufacturing plants in the US, Germany, Taiwan and Japan. Be that as it may, neither this company nor any other Taiwanese company linked to the development of integrated circuits and artificial intelligence (AI) can afford to lose human capital. And they are losing it. Taiwan investigates 100 cases in its “silent technology war” against China The Investigation Bureau of the Ministry of Justice of Taiwan is investigating 11 Chinese companies due to their possible involvement in recruiting talent in semiconductors, AI and other sectors linked to high-tech development, according to SCMP. Since 2020, the Government of Taiwan is dealing with 100 cases of possible talent theft in the field of engineering, and it is no coincidence. China has launched a huge talent search campaign in semiconductors and AI against the backdrop of its deep technological rivalry with the US. The 11 Chinese companies under investigation have been accused of illegally recruiting engineers The 11 Chinese companies that are being investigated by the Taiwanese Administration have been accused of illegally recruiting engineers by hiding their continental origin, creating front companies and establishing commercial operations in Taiwan without government approvalaccording to the Investigation Bureau of Taiwan’s Ministry of Justice. Abishur Prakash, a geopolitics expert at the Canadian consultancy ‘The Geopolitical Business’, maintains that: “This is a silent technological war compared to the noisy fight between the US and China (…) While the US focus usually lies on export controls or attracting foreign capital, the Chinese focus is on those critical pieces, such as talent, that will drive the next innovations in AI. Taiwan is fully aware of this.” One of the Chinese companies that are in Taiwan’s sights due to their possible involvement in talent theft is SMIC (Semiconductor Manufacturing International Corp), the largest Chinese semiconductor manufacturer with a global market share of about 5%. This company is the best asset that Xi Jinping’s Government currently has to sustain China’s technological development. Hua Hong Semiconductor and SMES (Semiconductor Manufacturing Electronics Shaoxing) are also two very important chip manufacturers, but the real spearhead of this gigantic Asian country in this industry is SMIC. This company is partially public and has, as expected, the support of the Chinese Government. Image | Generated by Xataka with Gemini More information | SCMP In Xataka | We already know what the chips that will arrive until 2039 will be like. The machine that will allow them to be manufactured is close

How to create simple Claude Skills to have your personalized version of artificial intelligence

by

Let’s explain to you how to create your own Claude Skilland thus have a personalized version of the artificial intelligence from Anthropic. The Claude’s Skills They are a series of instructions that you can upload to a chat so you don’t have to repeat them every time you want to give a specific compliment. Let’s start the article by reviewing what exactly the skills of Claude. And then, we are going to tell you step by step how to create a skill in the simplest way possible. What exactly are Claude’s Skills? Skills or abilities are a system with which you can create Claude customizations. With them, you can add a command layer to the generic versionand thus be able to use a version of the AI ​​adapted to what you want. A skill is an encapsulated procedurethe way to tell Claude how to perform specific tasks, under what conditions and with what rules you want him to do it, without having to repeat these instructions in every conversation. Imagine that you use Claude to repeatedly do specific tasks. Every time you want to do one of these tasks in a new chat you will have to describe what you want, something that can be tedious, especially when the instructions are longer and more complex. Skills allow you to encapsulate these instructions, so that when you activate one, these instructions are implicit in what you ask of it. When you write the prompt, Claude will first read the ability and take into account what you ask of him there. For example, imagine that you like to analyze the SEO of something you write about. So, every time you go to ask for this analysis you have to give the instructions to Claude, but If you load a Skill you do not need to give the instructionsand you can simply activate it and write the text you want to analyze. How to create your own Skills To create your own Claude skill, you need to open the AI ​​and click on the section Personalize that you have in the left column. Remember that Skills are a paid function. When you click on Personalizeyou will access two different options. On this screen, you must click on the option Skills that will appear next to the connectors. You will enter the Skills page, where by default you will see several examples of those created within Claude himself. Here, click on the + button above, and in the menu that opens choose the option Write the instructions for the skill to create one in the simplest way. This will take you to the screen where you will have to fill out the three fields necessary to create your Skill. You will have to give it a name, instructions and a knowledge base in the event that the latter is necessary. Three fields to define your new Skill The first thing you have to do is give your skill a name. This is the distinctive name it will have, and with which it will appear in your list of created Gems. It is recommended that it be a clear and distinctive name. The name will appear as if it were a file, with hyphens instead of spaces and in lower case. Then you will have to specify description. It’s a short description that will appear overlaid when you mouse over it in the skills list. Therefore, you have to write a short summary of what you do. Claude will look at your skills in each prompt you write, to use it in case he detects that you have referred to one of them with the task you have asked of him. That is why it is important to have useful and direct information in the name and descriptionso that both the AI ​​and you can distinguish what each one is for. Then comes the most complex part, because you will have to write detailed instructions of skill. This is the most important step, because it serves to define the role, tone and rules that this automation must follow. You have to specify everything you can when you are going to write these instructions. These are some of the most important aspects to include in the instructions when you go to create your Skill: Personality: You will have to say what their role is, the character they should play and the tone they should use. For example, you can ask them to act like a rigorous but friendly college professor, or a light-hearted, Reels-focused content writer. Whatever you want, but this personality is important to define to establish behavior. Objective and rules: It is also equally important to specify what the main task of the Gem is, and what rules to use. For example, you can say, “Your job is to review the texts to find spelling and grammar errors and improve the structure,” for example. You can also say things like “Never talk about topics other than…” to make him focus on that specific task. Format: This is optional, but you will also be able to define the structure of the answers. For example, you can ask that I always start with a summary and then list in several points, or whatever you think is necessary. In the end, the point is to define a response structure that is useful and in line with the tasks you want this Gemini customization to perform. If you don’t clarify by writing the instructionsyou have the option of using Claude himself to help you write them. To do this, open the AI ​​in another browser tab, and in a chat ask it to generate instructions for creating a Skill, adding a couple of instructions from which to start. And that’s it. Once you have created a Skill, all you have to do is choose it from the menu from Claude’s new chat. You will have to press the + button, go to Skills, and choose yours. Once … Read more

How to create a paper cut illustration from your photos with artificial intelligence, using ChatGPT or Gemini

by

Let’s tell you how to create a paper cut illustration from your photos using artificial intelligence. We are going to tell you a prompt that you will be able to use in both ChatGPT and Gemini, although the result can vary greatly depending on which of them you use. Therefore, we will start by telling you the prompt that you should copy and paste, which is quite long and detailed. And then we will tell you the differences between using Gemini and ChatGPT to do this, because they are very notable differences. Illustration of paper cut from your photos To make this composition, you simply have to add a photo and paste the text to the prompt What are you going to introduce to artificial intelligence? Then, the AI ​​will analyze the content of the photo and generate the result. This is the textual prompt that you must add: “Turn this image (attached) into a soft illustration style by layering handmade cut-out paper, inspired by the aesthetics of papercraft dioramas. Use soft, rounded shapes, adorable, simplified character proportions, and minimal facial details (point eyes, rosy cheeks) to create a warm, charming look. Apply stacked layers of paper with visible depth, subtle shadows between layers, and clean cut edges reminiscent of laser-cut cardboard. Add a distinctive white outer layer surrounding each main character, similar to a thick sticker border or a cut-out white paper backing, clearly separating the characters from the background. This white layer should look like an intentional paper layer, not a glow or halo. Use a pastel color palette with muted blues, greens and warm neutrals, balanced and calming. Lighting should feel soft, diffuse and uniform, enhancing dimensional paper layers without harsh contrasts. Textures should appear matte and tactile, like thick art paper or EVA foam. Overall mood: Cozy, endearing, delicate and story-like, with a playful yet polished handcrafted look, suitable for modern illustration, children’s books or decorative art.​​​​​​​​​​​​​​​​​​​ Then, you only have to wait a few seconds and you will get the result. This will vary very noticeably depending on the AI ​​model you are going to use. As you can see, it is a very VERY long prompt, but since we have translated it into Spanish you will be able to read it, review it and even make changes. Differences between Gemini and ChatGPT results Gemini does the paper cut style best. Gemini does the cut paper style better when creating the resulting image from your photos. The result is very beautiful, smooth and with very schematic images. However, does not capture characteristic features very welland in the case of animals it can even change the color of their hair. ChatGPT captures details much better ChatGPT captures colors and details betterthe characters that appear in the images are much more recognizable. However, the cut-out paper is not made in layers like in Gemini, the style is much less artistic, and looks more like stickers overlaid on a background. Therefore, there are no perfect results, and it will be up to you to do tests and see what you prefer, whether realism or more of an effect of overlapping cut-out papers. Taking into account that each AI offers results with its own personality, you will have no problems choosing one or the other depending on the photo and the result you want. In Xataka Basics | How to create an image of yourself and a Pixar character with your face using artificial intelligence, with Gemini or ChatGPT

How to use artificial intelligence at Easter to help you organize your trip or your long weekend vacation

by

We are going to tell you several things in which AI can help you during Easter. This can range from prior preparations to some help once you are there. You already have at your disposal a large number of apps and websites to organize yourself during Holy Weekbut so much Claude as ChatGPT either Gemini They can also help you by fulfilling several of the functions of these apps, and having them all in one. You should know that these are just ideas on how to apply the artificial intelligence in travel planning, but You should not blindly trust anything they tell you.because they can make mistakes. However, there are some applications that are quite useful, and I must even tell you that I keep a couple of them to myself after having discovered them researching for the article. Ask me to help you choose your destination If you still don’t know where to go At Easter, even knowing that accommodation may already be full in many destinations, you can also ask the AI ​​to give you suggestions on where to go. Thus, depending on the parameters you give it, it will make suggestions that adapt to what you have in mind. To do this, you have to create a prompt in which you give him some notions of what9 you want. You can tell it if you want the beach, mountains or city, if you are traveling alone, as a couple or as a family, and how many days you have available. You can also give him ideas about your budget.and ask him to give you several suggestions explaining the reason for each one. You can use a prompt like this: “I want to go on an Easter vacation from April 3 to 6, we are two adults, we like cities with history but that are not overcrowded, we have a medium-low budget and we leave from Valencia. What destinations would you recommend?” Create a day-by-day itinerary Once you have chosen the destination you want to go to, artificial intelligence can also help you create a complete day-by-day itinerarysuggesting and organizing the most recommended visits in a logical manner, and with more or less adjusted times. This is something that can always take a lot of time to do by hand, and even if you don’t want to trust 100% of what the AI ​​tells you, it can serve as a starting point that you can later adapt. You can use a prompt like this: “I’m going to spend 4 days in Seville from April 3 to 6. We are two people, we are interested in architecture, gastronomy and historic neighborhoods, but we want to avoid long lines and the most touristy sites. Can you make me a day-by-day itinerary with morning, afternoon and night?” Claude has a route planner Some AIs have their own route planning system. For example, you can plan routes with Claude with an internal mechanism that asks you several questions to find out what you want. This mechanism works for you to plan new routes and create a map module from an already created one. For example, if you have created a four-day route, then you only have to write the following: “Group everything in one map module” When you do this, a map module will be generated within Claude, with tabs for each of the days and a list of places you plan to go. These sites will be linked on the map so you know where to go from, and you can open the route in Google Maps. Create specialized AI You have two very good alternatives to create an AI specialized in the destination using only the documents that you give him as a knowledge base. The best of them is use NotebookLMbecause in addition to uploading PDFs and other files you can also add YouTube videos or websites as sources from which you will get the information. You can also use Claude. The advantage in both cases is that have control of the fonts you usebeing able to add travel guides that you trust to the sources, or official websites where all the first-hand information is available. Ask him to make your suitcase list I must admit that I am terrible at organizing my suitcase, and this is something that AI can also help you with. You can ask him to creates a list of things to take which will be personalized depending on your destination, the duration of the trip and the activities you are going to do. You can use a prompt like this: “I’m going to spend 5 days on the Costa Brava during Easter. There will be some hiking, trips to the beach if the weather is good and some dinner at a restaurant. Can you make me a complete packing list, including clothes, shoes, toiletries and various items?” In case you decide to use Claude, since he can make you a interactive packing list with a check list so that you can complete all the items you have included and know which ones you are missing. If you prefer you can also dictate to the AI ​​the things you want to have on your list of luggage, so that it is personalized. Then, when something else occurs to you, you can go to the chat you have with the AI ​​for this and ask it to add or remove items, or even ask it if you are missing something considering when and where you are going. Gemini finds flights for you and compares prices Although all AI chatbots can help you search for flights, Gemini integrates Google Flights along with the rest of Google tools. That makes the search engine company’s AI the best alternative to search for flights and give you all the information about prices and availability. To use this function you can ask directly for flight options from your city of origin to your destination by specifying the dates, and the … Read more

Log In

Forgot password?

Forgot password?

Enter your account data and we will send you a link to reset your password.

Your password reset link appears to be invalid or expired.

Log in

Privacy Policy

Add to Collection

No Collections

Here you'll find all collections you've created before.