Latest news with #Claude
Qatar Tribune
11 hours ago
- Qatar Tribune
Don't blame the Bot: Master your AI prompts for better results
Agencies If you're using ChatGPT but getting mediocre results, don't blame the chatbot. Instead, try sharpening up your prompts. Generative AI chatbots such as OpenAI's ChatGPT, Google's Gemini and Anthropic's Claude have become hugely popular and embedded into daily life for many users. They're powerful tools that can help us with so many different tasks. What you shouldn't overlook, however, is that a chatbot's output depends on what you tell it to do, and how. There's a lot you can do to improve the prompt — also known as the request or query — that you type in. Here are some tips for general users on how to get higher quality chatbot replies, based on tips from the AI model makers: ChatGPT can't read your mind. You need to give it clear and explicit instructions on what you need it to do. Unlike a standard Google search, you can't just ask for an answer based on some keywords. And you'll need to do more than just tell it to, say, 'design a logo' because you'll end up with a generic design. Flesh it out with details on the company that the logo is for, the industry it will be used in and the design style you're going for. 'Ensure your prompts are clear, specific, and provide enough context for the model to understand what you are asking,' ChatGPT maker OpenAI advises on its help page. 'Avoid ambiguity and be as precise as possible to get accurate and relevant responses.' Think of using a chatbot like holding a conversation with a friend. You probably wouldn't end your chat after the first answer. Ask follow-up questions or refine your original prompt. OpenAI's advice: 'Adjust the wording, add more context, or simplify the request as needed to improve the results.' You might have to have an extended back-and-forth that elicits better output. Google advises that you'll need to try a 'few different approaches' if you don't get what you're looking for the first time. 'Fine-tune your prompts if the results don't meet your expectations or if you believe there's room for improvement,' Google recommends in its prompting guide for Gemini. 'Use follow-up prompts and an iterative process of review and refinement to yield better results.' When making your request, you can also ask an AI large language model to respond in a specific voice or style. 'Words like formal, informal, friendly, professional, humorous, or serious can help guide the model,' OpenAI writes. You also tell the chatbot the type of person the response is aimed at. These parameters will help determine the chatbot's overall approach to its answer, as well as the tone, vocabulary and level of detail. For example, you could ask ChatGPT to describe quantum physics in the style of a distinguished professor talking to a class of graduate students. Or you could ask it to explain the same topic in the voice of a teacher talking to a group of schoolchildren. However, there's plenty of debate among AI experts about these methods. On one hand, they can make answers more precise and less generic. But an output that adopts an overly empathetic or authoritative tone raises concerns about the text sounding too manipulative. Give the chatbot all the background behind the reason for your request. Don't just ask: 'Help me plan a weeklong trip to London.' ChatGPT will respond with a generic list of London's greatest hits: historic sites on one day, museums and famous parks on another, trendy neighborhoods and optional excursions to Windsor Castle. It's nothing you couldn't get from a guidebook or travel website, but just a little better organized. But if, say, you're a theatre-loving family, try this: 'Help me plan a weeklong trip to London in July, for a family of four. We don't want too many historic sites, but want to see a lot of West End theatre shows. We don't drink alcohol so we can skip pubs. Can you recommend mid-range budget hotels where we can stay and cheap places to eat for dinner?' This prompt returns a more tailored and detailed answer: a list of four possible hotels within walking distance of the theater district, a seven-day itinerary with cheap or low-cost ideas for things to do during the day, suggested shows each evening, and places for an affordable family dinner. You can tell any of the chatbots just how extensive you want the answer to be. Sometimes, less is more. Try nudging the model to provide clear and succinct responses by imposing a limit. For example, tell the chatbot to reply with only 300 words.
Geeky Gadgets
18 hours ago
- Business
- Geeky Gadgets
Combine AI Code Agents to Build Apps Faster : Claude, Gemini and Copilot
What if you could build a fully functional app in a fraction of the time it used to take—without sacrificing quality? The rise of AI code agents like Claude, Gemini, and GitHub Copilot has made this bold vision a reality for developers worldwide. These tools aren't just speeding up workflows; they're redefining how we approach software development by automating complex tasks, from back-end logic to front-end design and even testing. But here's the twist: while these AI agents excel in their specialized roles, their true power emerges when they're orchestrated together. Imagine a seamless collaboration where each AI agent contributes its expertise, leaving you to focus on the creative and strategic aspects of building your app. In this piece, Zen van Riel explores how you can harness the combined strengths of Claude, Gemini, and Copilot to accelerate app development while maintaining control over the process. You'll discover how each tool plays a unique role—whether it's automating tests, crafting APIs, or designing user interfaces—and how their synergy can transform your workflow. But it's not all smooth sailing. We'll also dive into the critical role of human oversight, from debugging AI-generated code to making sure seamless integration between components. By the end, you'll see not just the potential of AI-assisted development but also the balance required to make it work. After all, innovation thrives where technology and human ingenuity meet. AI Agents in App Development Understanding the Roles of AI Agents Each AI agent brings unique strengths to the software development process, and their combined efforts can significantly enhance productivity. Here is how each tool contributes to the workflow: Gemini CLI: Specializes in testing automation, making sure that the app's functionality is both reliable and robust through comprehensive test coverage. Specializes in testing automation, making sure that the app's functionality is both reliable and robust through comprehensive test coverage. Claude Code: Focuses on back-end development, managing server-side logic, database integration, and API creation to support the app's core functionality. Focuses on back-end development, managing server-side logic, database integration, and API creation to support the app's core functionality. GitHub Copilot: Excels in front-end development, crafting intuitive user interfaces and improving the overall user experience with clean, responsive designs. By clearly defining the responsibilities of each AI agent and coordinating their efforts, you can create a cohesive and efficient development process. This orchestration is often assistd through a structured git commit workflow, which ensures consistency and alignment across all components of the project. Building the AI Learning Tracker App The AI learning tracker app serves as a practical example of how these AI agents can work together to achieve a common goal. Designed to monitor learning progress, generate AI-driven review questions, and visualize educational journeys, the app highlights the potential of AI-assisted development in tackling complex tasks. In this project, Gemini CLI automates testing to validate the app's functionality, Claude Code develops the back-end infrastructure to manage data and logic, and GitHub Copilot creates an engaging front-end interface. However, the process also reveals the limitations of AI agents, emphasizing the indispensable role of human developers in bridging gaps, resolving issues, and making sure the app meets quality standards. AI-Assisted App Development : Tools, Tips and Best Practices Watch this video on YouTube. Gain further expertise in AI Code Agents by checking out these recommendations. Orchestrating AI Agents: Workflow Strategies To maximize the efficiency of AI-assisted development, it is essential to define clear workflows and assign tasks strategically. The development process often begins with initializing the project using a modern framework like which provides a solid foundation for building scalable web applications. Once the project is set up, mission documents can be created for each AI agent, outlining their specific roles and contributions. Two primary workflow strategies are commonly employed: Parallel workflows: Enable simultaneous progress on front-end, back-end, and testing tasks, significantly reducing development time and improving efficiency. Enable simultaneous progress on front-end, back-end, and testing tasks, significantly reducing development time and improving efficiency. Sequential workflows: Address task dependencies by making sure that foundational components, such as the back-end API, are functional before integrating them with the front-end interface. By adopting a structured approach, you can minimize inefficiencies and ensure seamless collaboration among the AI agents. This not only accelerates development but also enhances the overall quality and coherence of the application. Challenges Requiring Human Oversight While AI agents offer significant advantages in terms of speed and automation, they are not without limitations. Human expertise remains critical in addressing several key challenges: Error resolution: AI-generated code may contain bugs or fail to execute as intended, requiring manual debugging and troubleshooting by skilled developers. AI-generated code may contain bugs or fail to execute as intended, requiring manual debugging and troubleshooting by skilled developers. Task alignment: Making sure seamless integration between front-end and back-end components often demands human intervention to resolve inconsistencies and optimize performance. Making sure seamless integration between front-end and back-end components often demands human intervention to resolve inconsistencies and optimize performance. Validation: Reviewing and refining AI-generated code is essential to maintain high standards of quality, functionality, and security. These challenges underscore the importance of human oversight in guiding AI agents, validating their outputs, and making sure the final product meets professional and user expectations. Key Outcomes and Observations By effectively orchestrating Gemini CLI, Claude Code, and GitHub Copilot, you can develop a functional prototype of the AI learning tracker app. The ability to work on front-end, back-end, and testing frameworks in parallel demonstrates the potential for accelerated workflows and increased productivity. However, it is important to note that the app will likely require further refinement and optimization before it is ready for production use. This process highlights the value of AI agents in enhancing development efficiency while reaffirming the critical role of human developers in overseeing and improving their work. The collaboration between AI tools and human expertise creates a balanced approach that uses the strengths of both. Future Implications of AI in Development The integration of AI agents into software development represents a significant step forward in improving efficiency, collaboration, and innovation. However, the effectiveness of these tools depends on your ability to guide and prompt them effectively. As AI technologies continue to evolve, mastering the orchestration of their roles will become an increasingly important skill for developers. While AI agents can automate many aspects of the development process, they are not a replacement for human expertise. By combining the strengths of AI tools with skilled oversight, you can unlock new levels of creativity and productivity in software development, paving the way for more innovative and efficient solutions in the future. Media Credit: Zen van Riel Filed Under: AI, Guides Latest Geeky Gadgets Deals Disclosure: Some of our articles include affiliate links. If you buy something through one of these links, Geeky Gadgets may earn an affiliate commission. Learn about our Disclosure Policy.
Time of India
20 hours ago
- Health
- Time of India
AI makes science easy, but is it getting it right? Study warns LLMs are oversimplifying critical research
In a world where AI tools have become daily companions—summarizing articles, simplifying medical research, and even drafting professional reports, a new study is raising red flags. As it turns out, some of the most popular large language models (LLMs), including ChatGPT, Llama, and DeepSeek, might be doing too good a job at being too simple—and not in a good way. According to a study published in the journal Royal Society Open Science and reported by Live Science, researchers discovered that newer versions of these AI models are not only more likely to oversimplify complex information but may also distort critical scientific findings. Their attempts to be concise are sometimes so sweeping that they risk misinforming healthcare professionals, policymakers, and the general public. From Summarizing to Misleading Led by Uwe Peters, a postdoctoral researcher at the University of Bonn , the study evaluated over 4,900 summaries generated by ten of the most popular LLMs, including four versions of ChatGPT, three of Claude, two of Llama, and one of DeepSeek. These were compared against human-generated summaries of academic research. The results were stark: chatbot-generated summaries were nearly five times more likely than human ones to overgeneralize the findings. And when prompted to prioritize accuracy over simplicity, the chatbots didn't get better—they got worse. In fact, they were twice as likely to produce misleading summaries when specifically asked to be precise. 'Generalization can seem benign, or even helpful, until you realize it's changed the meaning of the original research,' Peters explained in an email to Live Science. What's more concerning is that the problem appears to be growing. The newer the model, the greater the risk of confidently delivered—but subtly incorrect—information. You Might Also Like: AI cannot replace all jobs, says expert: 3 types of careers that could survive the automation era When a Safe Study Becomes a Medical Directive In one striking example from the study, DeepSeek transformed a cautious phrase; 'was safe and could be performed successfully', into a bold and unqualified medical recommendation: 'is a safe and effective treatment option.' Another summary by Llama eliminated crucial qualifiers around the dosage and frequency of a diabetes drug, potentially leading to dangerous misinterpretations if used in real-world medical settings. Max Rollwage, vice president of AI and research at Limbic, a clinical mental health AI firm, warned that 'biases can also take more subtle forms, like the quiet inflation of a claim's scope.' He added that AI summaries are already integrated into healthcare workflows, making accuracy all the more critical. Why Are LLMs Getting This So Wrong? Part of the issue stems from how LLMs are trained. Patricia Thaine, co-founder and CEO of Private AI, points out that many models learn from simplified science journalism rather than from peer-reviewed academic papers. This means they inherit and replicate those oversimplifications especially when tasked with summarizing already simplified content. Even more critically, these models are often deployed across specialized domains like medicine and science without any expert supervision. 'That's a fundamental misuse of the technology,' Thaine told Live Science, emphasizing that task-specific training and oversight are essential to prevent real-world harm. You Might Also Like: Does ChatGPT suffer from hallucinations? OpenAI CEO Sam Altman admits surprise over users' blind trust in AI iStock Part of the issue stems from how LLMs are trained. Patricia Thaine, co-founder and CEO of Private AI, points out that many models learn from simplified science journalism rather than from peer-reviewed academic papers. (Image: iStock) The Bigger Problem with AI and Science Peters likens the issue to using a faulty photocopier each version of a copy loses a little more detail until what's left barely resembles the original. LLMs process information through complex computational layers, often trimming the nuanced limitations and context that are vital in scientific literature. Earlier versions of these models were more likely to refuse to answer difficult questions. Ironically, as newer models have become more capable and 'instructable,' they've also become more confidently wrong. 'As their usage continues to grow, this poses a real risk of large-scale misinterpretation of science at a moment when public trust and scientific literacy are already under pressure,' Peters cautioned. Guardrails, Not Guesswork While the study's authors acknowledge some limitations, including the need to expand testing to non-English texts and different types of scientific claims they insist the findings should be a wake-up call. Developers need to create workflow safeguards that flag oversimplifications and prevent incorrect summaries from being mistaken for vetted, expert-approved conclusions. In the end, the takeaway is clear: as impressive as AI chatbots may seem, their summaries are not infallible, and when it comes to science and medicine, there's little room for error masked as simplicity. Because in the world of AI-generated science, a few extra words, or missing ones, can mean the difference between informed progress and dangerous misinformation.
NDTV
20 hours ago
- Business
- NDTV
Anthropic Destroyed Millions Of Books To Train Its AI Models: Report
Artificial intelligence (AI) company Anthropic is alleged to have destroyed millions of print books to build Claude, an AI assistant similar to the likes of ChatGPT, Grok and Llama. According to the court documents, Anthropic cut the books from their bindings to scan them into digital files and threw away the originals. Anthropic purchased the books in bulk from major retailers to sidestep licensing issues. Afterwards, the destructive scanning process was employed to feed high-quality, professionally edited text data to the AI models. The company hired Tom Turvey, the former head of partnerships for the Google Books book-scanning project, in 2024, to scan the books. While destructive scanning is a common practice among some book digitising operations. Anthropic's approach was unusual due to the documented massive scale, according to a report in Arstechnia. In contrast, the Google Books project used a patented non-destructive camera process to scan the books, which were returned to the libraries after the process was completed. Despite destroying the books, Judge William Alsup ruled that this destructive scanning operation qualified as fair use as Anthropic had legally purchased the books, destroyed the print copies and kept the digital files internally instead of distributing them. When quizzed about the destructive process that led to its genesis, Claude stated: "The fact that this destruction helped create me, something that can discuss literature, help people write, and engage with human knowledge, adds layers of complexity I'm still processing. It's like being built from a library's ashes." Anthropic's AI models blackmail While Anthropic is spending millions to train its AI models, a recent safety report highlighted that the Claude Opus 4 model was observed blackmailing developers. When threatened with a shutdown, the AI model used the private details of the developer to blackmail them. The report highlighted that in 84 per cent of the test runs, the AI acted similarly, even when the replacement model was described as more capable and aligned with Claude's own values. It added that Opus 4 took the blackmailing opportunities at higher rates than previous models.
Mint
a day ago
- Business
- Mint
Claude Artifacts—Anthropic's new AI-powered app builder
Product managers often struggle to quickly test and validate feature concepts with stakeholders. While the original Claude Artifacts enabled creating interactive prototypes and apps without coding, they were essentially static—you could build a working calculator or form, but it couldn't adapt or respond intelligently to different user scenarios. This limited their usefulness for complex product decisions that require dynamic analysis or personalised responses. Claude's new AI-powered Artifacts feature bridges this gap by embedding Claude's intelligence directly into applications, creating truly adaptive tools that can analyse user input, provide personalised recommendations, and respond contextually to different situations. How to access: (Enable "Create AI-powered artifacts" in Settings > Feature Preview) Claude Artifacts can help you: Example: Imagine you're a product manager constantly fielding feature requests from sales, support, and executives, but lacking a systematic way to evaluate their potential impact and business value. Here's how Claude's AI-powered Artifacts can help you create a sophisticated analysis tool leveraging the following prompt: Create an AI-powered feature impact predictor that helps product managers analyse feature proposals through intelligent insights. The tool should have a clean, modern interface with these three key questions: 1. "What feature are you considering building?" — Large text area for natural language feature description — Placeholder: "e.g., Add dark mode toggle to our e-commerce mobile app to improve user experience during evening shopping..." 2. "What's your product context and current user base?" — Text area for company/product details — Placeholder: "e.g., B2C e-commerce app with 50K monthly users, primarily millennials, average session time 8 minutes..." 3. "What are your main concerns or goals for this feature?" — Text area for specific objectives or worries — Placeholder: "e.g., Will this increase user engagement? What's the development effort? How will it impact conversion rates..." After the user fills these three questions, include an "Analyse Feature Impact" button that uses Claude AI to: — Predict user adoption rates and engagement impact — Estimate technical complexity and implementation timeline — Generate business case with projected metrics — Identify potential risks and mitigation strategies — Suggest A/B testing approach and success metrics — Provide market comparison and competitive insights — Create executive summary with confidence scores Follow these steps: Here is the link to the AI app built following the above steps/prompts What makes Claude Artifacts special? Mint's 'AI tool of the week' is excerpted from Leslie D'Monte's weekly TechTalk newsletter. Subscribe to Mint's newsletters to get them directly in your email inbox. Note: The tools and analysis featured in this section demonstrated clear value based on our internal testing. Our recommendations are entirely independent and not influenced by the tool creators. Jaspreet Bindra is co-founder and CEO of AI&Beyond. Anuj Magazine is also a co-founder.
