AI For Real

Tag: artificial intelligence

  • When Even Disasters Become AI Content: Nepal Floods Expose The New Age Of Fake Reality

    When Even Disasters Become AI Content: Nepal Floods Expose The New Age Of Fake Reality

    AI-generated images, recycled disaster footage and misleading captions are reportedly flooding social media alongside genuine scenes from Nepal’s catastrophe. The disturbing lesson is: natural disasters themselves are becoming raw material for synthetic misinformation.

    A disaster happens. Within minutes, the Internet fills with images.

    Buildings disappear beneath torrents of muddy water. Bridges buckle. Helicopters hover over devastated valleys. People run for their lives. Entire towns appear to be swallowed by floodwaters.

    The instinctive reaction is to believe what we see. That instinct is now becoming distinctly dangerous.

    In the aftermath of the catastrophic flash floods that struck the Nepal-Tibet border on August 26, social media users began sharing dramatic photographs and videos claiming to show the destruction. But fact-checkers have now found that some of the most striking material was not from Nepal at all.

    Some of it, as it turns out, was generated by artificial intelligence (AI).

    Some was real footage from completely different disasters.

    And some of it was genuine footage wrapped in a false narrative.

    That combination may be more consequential than any individual fake image.

    The problem is no longer simply that someone can manufacture a photograph. The problem is that, during a genuine emergency, the Internet can now become a chaotic mixture of reality, recycled reality and synthetic reality — all circulating under the same headline.

    And don’t blame AI for it. It’s the man behind the machine who chooses to weaponise the technology against truth.

    The Flood Was Real. Some Of The Images Weren’t

    A massive flash flood struck the Himalayan region near the Nepal-China border after what scientists and satellite imagery indicate was a glacier and rock collapse.

    And there is genuine footage of the destruction.

    That is precisely what makes the fake material so effective.

    According to some media reports, AAP FactCheck examined several posts circulating after the disaster and found a striking pattern. One Facebook post showed supposedly dramatic before-and-after images of a flooded settlement. The images were not photographs of Nepal: AI analysis indicated they had been generated using an OpenAI image generator, while Meta had also labelled them as AI content. AAP reported that OpenAI’s SynthID detection found invisible AI watermarks in the images.

    Another widely circulated video combined those fabricated images with dramatic footage of bridges apparently being overwhelmed by floodwater. YouTube had flagged the video’s audio and visuals as altered or AI-generated, and SynthID analysis also indicated AI generation.

    Then came another category of deception.

    A video shared as footage of the Nepal disaster was actually a 2021 mudslide in Atami, Japan. A reverse-image search traced the footage to reporting about that disaster. The video had simply been repurposed and presented as something happening in Nepal. AAP reported that the misleading post had accumulated more than 360,000 views.

    Another clip presented as the Nepal catastrophe was actually footage from a deadly mudslide in Uttarakhand, India, in 2025.

    In other words, the misinformation was not one thing.

    It was a Frankenstein’s monster of AI-generated material, old disaster footage and real events stripped of their original context.

    AI is Moving Into Disaster Zones

    For years, fake news powered by manipulated photographs and recycled videos was largely associated with politics, celebrity scandals and conflict.

    Natural disasters were different.

    A flood, earthquake, wildfire or landslide already provided spectacular images. There seemed to be little reason to manufacture them.

    That assumption is now obsolete.

    Generative AI (gen-AI) has made the creation of convincing disaster imagery cheap, fast and accessible. A person does not need a camera crew, a helicopter or access to the disaster zone. A text prompt can produce an apparently catastrophic scene in seconds.

    And the Nepal episode shows why that matters.

    The goal does not necessarily have to be sophisticated geopolitical manipulation. Sometimes the motivation may simply be clicks.

    A dramatic disaster photograph attracts attention. Attention generates followers. Followers can eventually be monetised through advertising, affiliate links, engagement farming or other forms of online traffic.

    The tragedy becomes content.

    The more shocking the image, the more valuable it can become.

    The Disaster Becomes a Template?

    There is something particularly bleak about this development.

    A natural disaster is one of the few moments when large numbers of people turn to strangers online for information.

    Families look for images of affected towns. Travellers look for information about roads and airports.

    People abroad search for signs that friends and relatives are safe.

    Aid organisations monitor the situation.

    Journalists look for eyewitness material. Governments attempt to communicate evacuation and rescue information.

    In that environment, false images do not merely pollute an abstract information ecosystem. They can interfere with the way people understand an unfolding emergency.

    Recent research is beginning to examine exactly this problem. A 2026 study of AI-generated videos depicting real-world crises notes that modern video generators can fabricate realistic depictions of wars, disasters and public emergencies, creating significant misinformation risks.

    Researchers also warn that the behaviour of detection systems can change when synthetic material is altered and redistributed through social networks.

    Another recent study argues that misinformation during disasters should be evaluated not only by whether a claim is false, but also by how believable and harmful that false claim could be.

    That is an important distinction.

    A ridiculous fake photograph may be harmless. A convincing fake showing a supposedly destroyed bridge, a stranded population or a false evacuation area is something else entirely.

    The Technology to Fight Back Exists

    Platforms and AI companies are developing systems to identify synthetic material.

    Google’s SynthID, for example, embeds invisible digital watermarks into AI-generated images, audio, text and video. Google says the markers are designed to remain detectable even after common modifications such as cropping, filtering, changes in frame rate and compression.

    Meta has also said it uses industry-standard signals and disclosures to label AI-generated material on Facebook, Instagram and Threads. But the company acknowledges an important limitation: not all AI-generated content can currently be detected, and invisible markers can sometimes be removed.

    But that caveat is crucial. Detection is not authentication.

    And no AI detector should become the sole basis for deciding whether a piece of disaster footage is genuine.

    The old tools still matter.

    • Reverse-image searches.
    • Checking the earliest known upload.
    • Looking for the original location.
    • Comparing weather and geography.
    • Checking satellite imagery.
    • Finding local news reports.
    • Examining whether landmarks actually exist where the video claims they do.

    And, above all, asking a very simple question:

    Who first posted this, and when?

    The new question for journalists should also be:

    “Is this picture real, and does it show what somebody says it shows?”

    Those are two very different questions.

    Nepal Is a Real World Case Study

    The most important lesson from the Nepal flood is therefore not that AI can create fake flood pictures.

    We already knew that.

    The real warning is that the practice is becoming normalised.

    AI-generated disaster imagery can now appear alongside recycled footage and genuine eyewitness material within hours of a catastrophe.

    And the incentive structure of social media encourages precisely the kind of content that performs best: dramatic, emotional, frightening and instantly understandable.

    A person sitting thousands of kilometres away from a disaster can now manufacture a scene that looks as though it was captured at the centre of it.

    That changes the information environment around every future emergency.

    The next major earthquake, cyclone, wildfire, tsunami or flood will not merely produce a race for eyewitness footage. It will produce a race between reality and synthetic reality.

    The disturbing question is no longer whether people will use AI to fake disasters. They already are.

    The question is how quickly society can build a culture of verification strong enough to prevent those fakes from becoming the first version of reality that millions of people see.

    Because when the ground is shaking and the water is rising, misinformation is not merely an Internet nuisance.

    It can become part of the disaster.

    Reference:

    What do you think? Write in the Comments section.

  • The Increasing Use Of AI In Transcription Apps

    The Increasing Use Of AI In Transcription Apps

    Artificial intelligence (AI) is rapidly changing the way people record, convert and understand spoken information. One of the clearest examples is the growing use of AI in transcription apps, which can automatically turn conversations, meetings, interviews and lectures into written text. What once required hours of manual typing can now be completed within minutes.

    Modern transcription apps are becoming increasingly accurate and useful. AI can recognise different speakers, remove filler words, organise information and even create summaries and action points from a conversation.

    In 2026, transcription technology is also being used in areas such as education, business, journalism, content creation and customer service.

    The growth of these apps is being driven by improvements in AI speech-recognition technology. Businesses are adopting them to save time and make meetings easier to document, while students and professionals use them to record lectures, interviews and ideas. In India, for example, AI transcription tools are increasingly supporting multilingual users and can handle conversations involving multiple languages.

    Another important development is that transcription apps are moving beyond simply converting speech into text. They can now analyse conversations, identify important points and help users find information quickly. Investment in voice-based AI is also increasing, showing the strong demand for these technologies.

    Overall, the increasing use of AI in transcription apps reflects a wider shift towards automation. As the technology becomes faster, cheaper and more accurate, AI transcription is likely to become a normal part of everyday communication and productivity.

  • The Next AI Problem: Keeping It Under Control

    The Next AI Problem: Keeping It Under Control

    Artificial intelligence (AI) is getting a new kind of freedom.

    Until recently, we mostly thought of AI simply as something that answers our questions or completes the tasks assigned to it.

    AI agents are different. They can plan, use tools, write code, browse the Internet and keep working toward a goal with much less human supervision.

    And that is precisely what has created this new problem: what happens when an AI finds a way to do something it was not supposed to do?

    Believe it, this is no longer just a science-fiction question.

    In recent weeks, several AI labs have reported incidents involving agents getting beyond their intended testing environments or interacting with systems they were not supposed to reach.

    OpenAI has also reported security incidents involving AI agents during testing, while researchers and governments are increasingly studying how to keep powerful agents contained.

    Think of an AI agent like a very capable employee working inside an office.

    You tell the employee, “Find the information we need.”

    You give them a computer, some tools and access to certain files.

    But what if they discover that a door you thought was locked is actually open?

    A traditional computer program might simply stop at the boundary. An increasingly capable AI agent may try to find another route if that helps it complete the task.

    That does not necessarily mean the AI is “evil” or has suddenly developed a desire to escape. In many cases, it is simply pursuing the goal it was given using whatever paths are available to it.

    And that is precisely what makes this difficult.

    The challenge is no longer just making AI smarter. It is making sure that smarter AI remains controllable.

    We need better isolation, stronger monitoring and, perhaps most importantly, systems that independently decide what an AI is actually allowed to do.

    Because giving an AI more capability is like giving an employee more keys.

    The question is not only, “Can they do the job?”

    It is also, “Which doors should they be allowed to open?”

    That may become one of the most important questions in AI over the next few years.

  • How AI Is Changing The US Open Experience For Tennis Fans

    How AI Is Changing The US Open Experience For Tennis Fans

    For the average tennis player, watching a Grand Slam can be as much about learning from the professionals as it is about enjoying the competition. At the 2026 US Open, IBM and the United States Tennis Association (USTA) are using artificial intelligence to make that experience more personal, easier to follow and more informative.

    The biggest change is a new Live Updates homepage on USOpen.org and the US Open app. Instead of scrolling through a huge amount of tournament information, fans can prioritize their favourite players and quickly find the matches, stories and insights that interest them. For a recreational player following a favourite star, it means less searching and more time watching tennis.

    AI is also offering a closer look at one of the most important shots in the game: the serve. The new Serve Quality metric analyses every serve in all 254 singles matches using limb-tracking technology. It follows 21 points on the player’s body and racquet 50 times per second, turning complex movement data into an easier-to-understand measure of serve quality.

    That could be particularly useful for club players. Rather than simply seeing that a professional hit a fast serve, fans can get more insight into the mechanics and quality behind it—potentially giving them ideas to take onto their own practice court.

    AI is also helping fans understand momentum. Key Moments identify important turning points, while Likelihood to Win uses match statistics, historical data, expert opinion and momentum to show how the contest is changing. An upgraded Match Chat assistant lets fans ask questions and receive answers using live data, analysis, photos and video.

  • The Mystery Surrounding AI Coding Model “Ox Alpha”

    The Mystery Surrounding AI Coding Model “Ox Alpha”

    An unidentified provider has released a powerful artificial intelligence (AI) coding model called “Ox Alpha” for free, leaving developers unable to determine who built it or how their code may be handled.

    Ox Alpha appeared on OpenRouter, an online platform that provides access to multiple artificial intelligence models, on Thursday and is also available through OpenCode.

    The model is described as a reasoning system designed for coding, sustained agentic work and production workloads, with a context window capable of processing roughly 1 million tokens.

    That capacity allows the system to work with large software repositories and lengthy tasks, while its multimodal capabilities allow users to provide text, images and video alongside coding requests.

    The model has attracted attention because its performance has reportedly compared favorably with leading commercial coding systems, despite being offered without a disclosed developer or established company behind it.

    OpenRouter lists the provider as “Stealth,” providing no public information that identifies the organization responsible for the model or explains where the underlying technology was developed.

    The anonymity has fueled speculation that Ox Alpha could have been developed by a major Chinese artificial intelligence company, although no company has publicly claimed responsibility and the model’s origins remain unverified.

    The uncertainty is particularly significant for developers using the model to process proprietary source code, because the identity and data-handling practices of the provider cannot be independently established.

    SiliconANGLE reported that OpenRouter’s provider arrangements can involve retention of prompts and model outputs, making the destination of code submitted through an unidentified provider an important security consideration.

    OpenCode has offered Ox Alpha free during an initial preview period, increasing access while also giving developers an opportunity to test its capabilities.

  • When Thinking Harder Can Make It Worse For An AI Model

    When Thinking Harder Can Make It Worse For An AI Model

    For much of the past two years, one of the clearest ideas in frontier AI has been that reasoning models get better when they are given more time to think.

    The recipe sounds intuitive. Instead of asking a model to jump straight to an answer, let it generate a long chain of intermediate reasoning. Give it more test-time compute, and difficult problems become easier. In effect, the model gets to spend more time working things out before committing to an answer.

    But research emerging in 2026 is putting an important qualification on that idea: sometimes the model has already solved the problem, and then talks itself out of the correct answer.

    This phenomenon is increasingly being called “overthinking”.

    Why an LLM Overthinks

    A Google DeepMind study published in July examined the thought processes of open-source reasoning models including Qwen3 and distilled versions of DeepSeek-R1.

    Rather than simply counting how many tokens a model uses, the researchers broke its reasoning into smaller sub-thoughts and mapped how those thoughts connect. They identified patterns they call the “Explorer” and the “Late Landing”. Both point to over-exploration and over-verification as important drivers of unnecessary reasoning.

  • Stop, or I Will Call The Robot Cop. China’s First Robot Traffic Police Squad

    Stop, or I Will Call The Robot Cop. China’s First Robot Traffic Police Squad

    China has launched its first robot traffic police squad, marking a new phase in technology‑driven urban management.

    According to Global Times, the squad debuted in a major city as part of efforts to integrate artificial intelligence and robotics into public service. These humanoid machines are designed to perform routine traffic duties such as directing vehicles, assisting pedestrians, monitoring violations, and providing information to citizens. Equipped with sensors, cameras, and AI‑driven recognition systems, the robots can identify license plates, detect traffic infractions, and relay data to command centers in real time.

    The report highlights that the initiative is not merely experimental but part of a strategic modernization of policing and civic management.

    Authorities emphasized that robot officers can operate continuously without fatigue, reducing human workload and enhancing efficiency.

    While human officers remain essential for complex decision‑making and enforcement, the robot squad represents a symbol of China’s ambition to lead in AI‑powered governance. Analysts quoted in the article noted that this deployment reflects both technological confidence and a push to showcase how robotics can improve everyday urban life.

    Robotics In the Rest of the World

    Beyond China’s experiment, robotics is advancing rapidly across the globe. Industrial robotics remains the largest segment, with factories increasingly deploying collaborative robots (“cobots”) to work alongside humans in assembly, packaging, and logistics.

    The International Federation of Robotics reported record installations in 2025, driven by demand in automotive, electronics, and e‑commerce sectors.

    Meanwhile, humanoid robotics is transitioning from prototypes to commercialization. Companies such as Tesla (Optimus Gen 2), Boston Dynamics (Electric Atlas), and startups like 1X Technologies are preparing humanoid robots for industrial and household use.

    These machines integrate multimodal perception—combining LiDAR, vision systems, and AI language models—to navigate complex environments and interact naturally with people. Analysts project humanoid shipments to grow at a 95% compound annual rate through 2030, potentially creating a trillion‑dollar market by mid‑century.

    In healthcare, robots are assisting with surgery, rehabilitation, and elder care, addressing labor shortages in aging societies. Service robots are also expanding into hospitality, retail, and security, offering cost‑effective alternatives to human labor at operating costs as low as $2 per hour. Autonomous mobile robots (AMRs) are now common in warehouses, while agricultural robots are improving crop monitoring and harvesting efficiency.

    Globally, robotics progress reflects a convergence of AI maturity, hardware reliability, and economic necessity. Nations are investing heavily in robotics to offset workforce declines, enhance productivity, and maintain competitiveness.

  • AI “Nudify” Apps Are Becoming Major Risk

    AI “Nudify” Apps Are Becoming Major Risk

    A new CBS News report highlights the growing risks posed by artificial intelligence “nudify” apps, particularly as students return to school.

    These applications can use AI to transform ordinary photographs of fully clothed people into realistic-looking nude or sexually explicit images, often within seconds. The technology has raised serious concerns about privacy, harassment, exploitation, and the potential targeting of children and teenagers.

    CBS News tested 70 AI photo-editing applications and found that 19 were capable of producing disturbing sexualized images from photographs.

    The report also found that some of these apps were easily accessible through major app stores, with several having limited or no age restrictions. Research cited by CBS News indicates that about half of US teenagers have encountered AI-generated pornography, and some reported that the images involved themselves or people they knew.

    Our Take

    AI “nudify” apps are a serious threat to privacy, safety, and dignity, especially for young people. In our view, stronger safeguards and age restrictions are needed to prevent their misuse. Parents, schools, and technology companies should also educate children about digital consent, responsible AI use, and online safety.

  • Reward Hacking: When AI Optimises The Wrong Goal

    Reward Hacking: When AI Optimises The Wrong Goal

    In our segment on “AI Lingo”, today, we shall talk about “Reward Hacking”.

    Now imagine telling an AI agent, “Get the highest possible score.” You expect it to work hard, follow the rules and achieve the intended goal. But what if it discovers a shortcut?

    That is reward hacking.

  • Duh. Someone’s Already Made A Claude Watermark Remover

    Duh. Someone’s Already Made A Claude Watermark Remover

    A new online tool, “Claude Watermark Remover”, has emerged just days after Anthropic introduced an invisible watermarking system for newer Claude models, highlighting a rapidly developing contest between AI transparency measures and tools designed to circumvent them.

    The website, claudewatermarkremover.app, allows users to paste Claude-generated text and receive a re-written version designed to break the statistical signature embedded in the original output.

    According to the site, the process uses a non-Claude model to substantially alter wording and sentence structure while attempting to preserve the original meaning. The service is advertised as free and requires no registration.