The Time Capsule Generator is an innovative application designed to help users capture, preserve, and revisit their life’s most meaningful moments using cutting-edge AI technology. By blending emotional storytelling with advanced natural language processing, this app allows users to create personalized digital time capsules that evolve with them over time. Whether documenting personal milestones, aspirations, or everyday thoughts, the app transforms ordinary memories into timeless keepsakes, delivering a unique blend of nostalgia and forward-looking inspiration. Key Features AI-Powered Time Capsule Creation: Users input details about their current life, goals, and emotions. The app leverages OpenAI’s GPT-3.5/4 model to generate three core elements: Reflective Summary: A snapshot of the user’s current state, capturing their mindset and experiences. Future Predictions: Fun, speculative insights about where life might take them. Letter from the Past: A heartfelt message from the user’s "past self" to their future self, adding a deeply personal touch. Scheduled Delivery: Users set a future date (e.g., 5 years later) to receive their time capsule. The app automatically sends the capsule via email on the specified date using a secure Gmail integration, ensuring privacy and reliability. Interactive Unboxing Experience: When a capsule is opened, the AI generates a new reflection comparing the user’s past and present. This feature analyzes the original content alongside any new input from the user, offering insights into personal growth, achievements, and changes over time. Social Sharing: Users can share their capsules on platforms like Facebook, WhatsApp, Instagram, and LinkedIn. Ideal for milestone celebrations, personal journaling, or legacy-building, the Time Capsule Generator redefines how we preserve memories in the digital age. By merging technology with humanity, it offers a timeless way to reflect on the past, navigate the present, and envision the future.

The problem we are trying to solve is that of accessibility of the internet by people to disabilities. Accessibility in the sense that people with disabilities eg, people with ADHD, find it hard to navigate through complex and long webpages and end up getting less from what is meant to benefit them the most. Our solutiion is Accessify, A chrome extension that uses generative AI (Gemini Ultra APIs) to be able to simplify the process of navigating through webpages. Gemini Takes in the webpage, summarises and gives a more comprehensible, understandable and storylike version of the website which can make it easy for them to navigate thorugh the site. Accessify also offers additional features such as images summarisation and it is also able to explain an image inthe context pf the words that is found around it. This will help those with poor vision, color blindness, etc to better understand their webpages. Also, a Text-to-Speech model also makes it easy for people who are blind or who just prefer spoken words to listen to the better version of the website. In the future, we hope to make Accessify open source and others can contribute to it. Other features that we will want to include oin the feature is saving preference data to be able to provide better services to our audience, improving the view of the extension, add other feaures like contrast enhancement, and integrate it with an IoT device - Braille writer that can help translate Words to Braille for those with visual impairment to use. We hope to see people with disabilitiies flourish despite their seemingly disadvantaged state, but with accessify, we can change the game. Thank you.

This project explores the advancement of predictive modeling within artificial intelligence, aiming to equip robots with the ability to forecast future events. This capability is designed to mirror the predictive thinking observed in humans, thus enhancing the practical applications and benefits of robotic systems in various sectors. The innovative approach taken involves a unique method of teaching AI systems, like Claude, to interpret and predict future scenarios based on visual inputs, similar to watching television. The methodology focuses on treating visual input as a series of storytelling frames. Claude, for instance, would analyze two given frames, understanding the content and actions within them, and then leverage its natural language generation capabilities to predict and describe what might occur in the subsequent frame. This project not only advances the field of predictive modeling in AI but also opens new pathways for interactive and anticipatory technologies, fostering a closer synergy between human cognitive processes and artificial intelligence.

We developed a tool using the Yi-34B-200k model that will take scientific abstracts and summarize them for a person deeply interested in life extension, which we will call a biohacker in this context. These people want to extend their lives to 200-500 years or even longer and take a wide variety of supplements and drugs to help them live longer. There is much scientific research in life extension and going through scientific papers to find the latest research is a daunting task for many biohackers who lack the education given to a medical doctor or researcher. By making summaries of these articles in a form that is easy to understand, it will help biohackers follow the latest scientific research more easily.

Text2Room is a groundbreaking innovation that redefines the process of 3D content creation. This transformative method harnesses the power of pre-trained 2D text-to-image models to generate room-scale textured 3D meshes from simple text prompts. Through an iterative scene generation process, Text2Room renders 3D meshes from diverse camera angles and seamlessly fuses missing details using advanced algorithms, resulting in immersive and captivating environments. What sets Text2Room apart is its two-stage viewpoint selection strategy – the Generation Stage creates the main scene layout, while the Completion Stage intelligently fills gaps, ensuring a complete and coherent 3D representation. By democratizing 3D content creation, Text2Room eliminates complexities and accelerates the process, making it accessible to a wide range of industries including AR/VR content, gaming, and architectural visualization. Text2Room isn't just a product; it's a creative revolution that empowers users to turn their imagination into tangible, interactive experiences. With limitless applications and an ever-growing market demand for immersive 3D content, Text2Room stands at the forefront of innovation, shaping the future of content creation.

In this hybrid hackathon powered by Arc, developers will build the next generation of agentic commerce systems using Arc with USDC. Explore a world where AI agents and web services can pay for APIs, data, compute, and content in dynamic, usage-based ways, while Arc provides stablecoin-native settlement with predictable USDC fees and deterministic, sub-second finality. This hackathon is supported by Google & Google DeepMind, with a dedicated challenge and $10,000 in Google Cloud Platform (GCP) credits awarded for the best use of Gemini models and Google AI Studio. 📅 January 9 – 24, 2026 • Jan 9 – 23 (Online Phase) – Collaborate and build online with developers and AI innovators from around the world. All projects must be submitted by the end of the online phase on January 23rd. • Jan 23 (On‑site Build Day – San Francisco, CA) – Selected participants will be invited to an exclusive in‑person session to refine their projects and connect directly with mentors. • Jan 24 (On‑site Demos & Awards – San Francisco, CA) – Live pitching sessions to a panel of judges and ecosystem partners, followed by the official winner announcement. Get guidance from Arc and Circle experts through on-site support. 📍 On-site Venue (Jan 23–24): MindsDB SF AI Collective 3154 17th St, San Francisco, California, USA 🤝 Go solo or team up, it's your flow. 🏆Compete for $10,000 in USDC & $10,000 in GCP Credits. 📍 On-site participation is by invitation only. Travel and accommodation expenses will not be covered. 🧑🏻‍💻 Secure your spot now - sign up before the Kick-Off Stream!

Join Deriv and lablab.ai for a high-intensity hybrid hackathon where top builders create AI prototypes, demo their work, and get fast-tracked to interviews. When • Sat, Jan 31, 2026- On-Site Pre-Hackathon: Deriv AI Meetup (Dubai) • Fri, Feb 6 - Opening words, Challenge, and Hackathon kick-off. (Dubai) • Sat, Feb 7 - Build and ship your prototype - 12 hours (Onsite +Online) • Sun, Feb 8 - Demos, judging, and next steps for standout teams. (Onsite +Online) On-Site Pre-Hackathon: Deriv AI Meetup Sat, Jan 31, 2026 · 2:00–6:00 PM (GST) · Dubai In-person talks, workshops, team formation, and networking with the Deriv team. 👉 Deriv AI Meetup registration What's in it for you • USD $10,000+ in prizes across categories • Mentors available to unblock you when you're stuck • Fast-track interviews for top performers - skip the queue • Real problems to solve - not toy demos Format • Teams of 1-3 • Hybrid: Dubai on-site or fully remote • On-site spots confirmed after screening Location • Deriv Office, Business Bay, Dubai • Travel and accommodation not provided. Apply now • Spots are limited. Shortlisting begins right after the event.

🗓️ 48-hour AI Challenge - Build your own AI agent or agent simulation over the weekend 🦜 Power up your coding with the LangChain framework! 🤝 Connect with potential co-founders and mentors at the event

⌚ 60-hour Hackathon to build AI apps with cutting-edge 3D generative models by OpenAI, Nvidia and Stable Diffusion 💡 Experiment with Point-e, Sharp-e, GET3D, Stable Diffusion's Dreamfusion 🚀 Build a fully functional AI app under the hackathon's tight timeline! 👥 Find teammates and get mentor support throughout the event

🔴 An advanced-level hackathon ⏱ The one-day challenge 🧑‍💻 Build with the next-gen technology 🏁 Complete your app by the end!