Event ended

Salz21 AI Hackathon Summary

Salz21 AI Hackathon image

Hackathon Overview

Our AI hackathon brought together a diverse group of participants, who collaborated to develop a variety of impressive projects based on:

616

Participants

53

Teams

12

AI Applications

Winners and Finalists

medal

Creator Alde

This app is a powerful tool designed to assist content creators who have a substantial following of over 5000 viewers or followers. By leveraging the YouTube API, the app can efficiently read through all the comments and classify them according to their sentiment, toxic content, or spam. After classifying the comments, the app creates a word embedding using cohere AI, which helps to identify patterns and group similar comments together. These comments are then grouped into three clusters using KMeans. By clustering the comments, content creators can quickly analyze and understand the nature of the comments and identify any common themes or topics that resonate with their audience. Using the analysis of the clustered comments, the app generates a summary of the main themes and extracts the primary topics. These topics are presented to the content creators, along with suggested content ideas for future posts. This helps content creators to understand the interests and preferences of their audience better and create content that resonates with their viewers. In conclusion, this app provides content creators with a streamlined approach to understanding their audience's preferences and interests by analyzing the comments on their posts. By classifying, clustering, and summarizing comments, the app provides a valuable tool for generating new content ideas that will engage and excite their audience, leading to increased views and followers.

Artificial Ducks

ChatGPTCohere Classify
medal

MultiplAI

MultiplAI is an API that takes in a base ad and outputs customized ads using various AI tools. The end goal is to generate more user engagement and a higher conversion rate. We use ChatGPT and Dall-E to convert the initial text and picture provided to us and customize it to one particular customer group, or even one particular customer, based on the data that is available about them. With increasing AI capabilities and more data being gathered for each individual user, big platforms and search engines will be able to not only cater the ads they show to a group of people, but literally personalize them for each individual user.

Red Hot Data Wizards

ChatGPTDALL-E-2
medal

Top Applicant Speedpass

Finding top applicants is a time consuming, rigorous process that involves juxtaposing many resumes for comparison. This process is messy and may overlook qualified candidates in favor of time. TAS is the ultimate time-saving intelligent tool that allows recruiters to select their top candidates to interview. Instead of reviewing each submission one-by-one, a list of resumes is uploaded to TAS and analyzed. All resume data is parsed via OCR to allow recruiters to input both text and image-based PDFs. The recruiter then specifies an assessment question ("Which of these candidates for Finance Manager has experience in the Aviation industry?") to which GPT-3's assessment of that criteria will be provided back to the recruiter.

AI-ku Poets

ChatGPTCohere ClassifyGANGPT-3
medal
Streamlit
application badge

Vi chat

Vi-chat is an innovative AI assistant aimed at helping mothers connect with their autistic children by converting their voice into images easily understood by autistic children as they are have difficulty processing spoken language but prefer pictures. we used openai model with their whisper and dall beta embedded to transform voice into images. this solution is never offered before to autistic children but it will help them communicate and boost their learning process. we plan to make this app go both ways from voice to image and from image to voice in near future and make it customized to every child and his preferences. We are very proud and honored to help autistic children and their mothers get connected together

Clawcode

WhisperDALL-E-2

Speakers, Mentors, and Organizers

Olesia Zinchenko profile picture
mentor

Olesia Zinchenko

Event Manager & Mentor at lablab.ai

Anastasiia Strakhova profile picture
mentor

Anastasiia Strakhova

Event Specialist at NewNative

    Liza Marchuk profile picture
    mentor

    Liza Marchuk

    Smm

      Pawel Czech profile picture
      speaker

      Pawel Czech

      Co-founder/Partner

        Mathias Asberg profile picture
        speaker

        Mathias Asberg

        founder

          Christoph Moosbauer profile picture
          mentor

          Christoph Moosbauer

          RTI Manager

          Ervin Moore profile picture
          mentor

          Ervin Moore

          PhD Computer Science Student

            Theodoros Ampas profile picture
            mentor

            Theodoros Ampas

            Co-Founder of Content-Hive

            Skander Karoui profile picture
            mentor

            Skander Karoui

            Data Science and AI enthusiast || ICT Engineer

              Gonzalo Huelmo Romero profile picture
              mentor

              Gonzalo Huelmo Romero

              Bachelor in Informatics / Data Science

              Dimitrije Pesic profile picture
              mentor

              Dimitrije Pesic

              Student

                Omar Sesa profile picture
                mentor

                Omar Sesa

                Assistant Lecturer in AI, ML and embedded systems field

                  Natasa Deutinger profile picture
                  speaker

                  Natasa Deutinger

                  Head of Startup Salzburg / Startup Coach

                    Simon Hirlaender profile picture
                    speaker

                    Simon Hirlaender

                    Researcher

                      This event has now ended, but you can still register for upcoming events on lablab.ai. We look forward to seeing you at the next one!

                      Checkout Upcoming Events →

                      Submitted Concepts, Prototypes and Pitches

                      Submissions from the teams participating in the Salz21 AI Hackathon event and making it to the end 👊

                      Help to spread the word and share these amazing projects!

                      Vercel
                      application badge

                      NeoLocus

                      A solution to help businesses place their products in custom environments using generative AI. For an e-commerce business, having an attractive listing of their inventory is crucial. Significant time and money is spent on: Photoshoots Mockups 3D renders For an e-commerce customer, the user journey for buying a furniture product faces challenges such as: Long research to find the perfect product. Imagining the product in their space. Product’s aesthetic fit with the rest of the space. So we have made a generative AI powered tool that helps Companies place their products in custom environments (with no prior knowledge on generative AI). This is done by custom trained diffusion models.

                      Neo-Locus

                      Stable DiffusionYOLOv7

                      PAAI

                      PAAI is a personal A.I. assistant that offers a customized and adaptable experience to help users streamline productivity, manage their personal information and assets, and improve their overall quality of life. PAAI can offer personalized learning and development opportunities to help users grow and reach their full potential, social support and companionship to reduce feelings of loneliness, health monitoring and advocacy, advisory within multiple domains. PAAI provides simplified access to information and communication, making it easy to find what users need when they need it, how they need it. PAAI is modular and sculpt-able designed to fit the unique interests and needs of each individual user, making it an all-in-one A.l. powered tool for maximum life enhancement.

                      Ad Astra

                      ChatGPT

                      Dripper News

                      a personalized news feed focused on the tech industry, powered by artificial intelligence (AI). Our news aggregator is specifically designed for busy CEOs, providing them with the latest and most relevant news in the tech sector. Through the use of AI, our platform curates and filters news articles from reputable sources, presenting only the most important and timely news stories to our users. This allows CEOs to stay informed on the latest trends, industry developments, and competitor updates in a quick and efficient manner. Additionally, our news aggregator provides a personalized experience for each user. By analyzing the user's reading habits and interests, our AI technology tailors the news feed to provide a custom selection of articles that are most relevant to their business and industry. Overall, our personalized news feed offers a comprehensive solution for CEOs who want to stay informed on the latest developments in the tech industry without the hassle of sorting through countless news sources. With our platform, CEOs can stay ahead of the curve and make informed decisions for their companies.

                      Dripper News

                      WhisperGPT-3
                      medal

                      Top Applicant Speedpass

                      Finding top applicants is a time consuming, rigorous process that involves juxtaposing many resumes for comparison. This process is messy and may overlook qualified candidates in favor of time. TAS is the ultimate time-saving intelligent tool that allows recruiters to select their top candidates to interview. Instead of reviewing each submission one-by-one, a list of resumes is uploaded to TAS and analyzed. All resume data is parsed via OCR to allow recruiters to input both text and image-based PDFs. The recruiter then specifies an assessment question ("Which of these candidates for Finance Manager has experience in the Aviation industry?") to which GPT-3's assessment of that criteria will be provided back to the recruiter.

                      AI-ku Poets

                      ChatGPTCohere ClassifyGANGPT-3

                      Shinyonaika

                      Shinyonaika, gamifies Cognitive Behaivioural Therapy into Storylines using Whisper + Cohere API to process User Emotion based on input given by user. It uses Unity for Game Development, C# for Scripting and powerful AI Models like Whisper+Cohere. CBT has 3 Steps: 1.Identify Negative Emotions 2.Identify Triggering Situations 4.Reshaping Negative Emotion It's goals are: Mental Health Awareness Making CBT Interactive and Graphical Self Therapy The product is new and has no competion. It can be made available to all Users, since, it uses technology that is common in the market. Note: Psychotherapists were consulted during development.

                      MAVERICKS

                      CohereWhisper
                      medal

                      MultiplAI

                      MultiplAI is an API that takes in a base ad and outputs customized ads using various AI tools. The end goal is to generate more user engagement and a higher conversion rate. We use ChatGPT and Dall-E to convert the initial text and picture provided to us and customize it to one particular customer group, or even one particular customer, based on the data that is available about them. With increasing AI capabilities and more data being gathered for each individual user, big platforms and search engines will be able to not only cater the ads they show to a group of people, but literally personalize them for each individual user.

                      Red Hot Data Wizards

                      ChatGPTDALL-E-2
                      medal
                      Streamlit
                      application badge

                      Vi chat

                      Vi-chat is an innovative AI assistant aimed at helping mothers connect with their autistic children by converting their voice into images easily understood by autistic children as they are have difficulty processing spoken language but prefer pictures. we used openai model with their whisper and dall beta embedded to transform voice into images. this solution is never offered before to autistic children but it will help them communicate and boost their learning process. we plan to make this app go both ways from voice to image and from image to voice in near future and make it customized to every child and his preferences. We are very proud and honored to help autistic children and their mothers get connected together

                      Clawcode

                      WhisperDALL-E-2

                      EasyQuery

                      EasyQuery is a revolutionary product that enables users to effortlessly harness the intuitive power of Web3 data query through natural language. With its ability to extract data insights and facilitate native data utilization in dApps, EasyQuery is the ultimate tool for unlocking the full potential of Web3. What is the problem EasyQuery aims to solve? First, Web3 data is scattered on various blockchains and platforms lacking connectivity. In addition, there is limited access to historical data for smart contracts. Second, It has been difficult to fetch and process the data for further implementation. There are high technical barriers for using existing data tool platforms. Third, creating data visualization and extracting business insights have been time consuming. Tech specs KNN3 Data services A data warehouse storing indexed and structured on-chain and off-chain data is provided. Built on top of it, stable and flexible database services are available for back-end support. OpenAI With the power of openAI, human language can be translated into SQL queries with proper prompt engineering. Two different prompt agents are used in this product, one is used for SQL generation and the other is used for data insights generation. Target Users There are two types of target users. The first group that could benefit from EasyQuery are developers who specialize in social dApp data/algorithm development or smart contract development, and require a convenient and efficient method for accessing Web3 data. The second group comprises individuals who are interested in Web3 data but lack extensive coding expertise. EasyQuery offers them the opportunity to obtain the desired data.

                      EasyQuery

                      OpenAI gymGPT-3
                      medal

                      Creator Alde

                      This app is a powerful tool designed to assist content creators who have a substantial following of over 5000 viewers or followers. By leveraging the YouTube API, the app can efficiently read through all the comments and classify them according to their sentiment, toxic content, or spam. After classifying the comments, the app creates a word embedding using cohere AI, which helps to identify patterns and group similar comments together. These comments are then grouped into three clusters using KMeans. By clustering the comments, content creators can quickly analyze and understand the nature of the comments and identify any common themes or topics that resonate with their audience. Using the analysis of the clustered comments, the app generates a summary of the main themes and extracts the primary topics. These topics are presented to the content creators, along with suggested content ideas for future posts. This helps content creators to understand the interests and preferences of their audience better and create content that resonates with their viewers. In conclusion, this app provides content creators with a streamlined approach to understanding their audience's preferences and interests by analyzing the comments on their posts. By classifying, clustering, and summarizing comments, the app provides a valuable tool for generating new content ideas that will engage and excite their audience, leading to increased views and followers.

                      Artificial Ducks

                      ChatGPTCohere Classify

                      Fudl app

                      Are you tired of overspending on groceries every month and wasting your time reviewing supermarkets' promo materials? Fudl is the answer to all your problems! Our revolutionary AI-powered app is designed to help you save money on your grocery bill without compromising on quality. With Fudl, you can plan your purchases, analyze discounts and special offers, discover analogs of products you need for less price, find more savings with value-sized items, and send your orders directly to the delivery service. Let me explain all the features in a more detailed way: By using Fudl's personalized recommendations, you can use your grocery budget to find the best deals on the products you need. Fudl's AI technology analyzes your shopping list, gives you recommendations based on your individual preferences, and suggests alternative products that are just as good, if not better, at a lower cost. Fudl's innovative technology also allows you to split one order into several from different grocery chains, which can save you up to 50% on your grocery bill. This means you can buy in for the next week or plan your purchases for the weeks ahead, without worrying about overspending. Using Fudl to split your order, you can save money and collect additional points from grocery loyalty programs while still getting the needed products. Fudl uses databases from online stores to provide you with the best possible recommendations. For this example, we tested our algorithms on three major chains in Slovenia - Mercator, Spar, and Tus and got phenomenal savings from 10 to 40% on single bills. To find the most successful alternative for each product, we utilize the power of AI to determine its coordinates in a multidimensional space. By doing so, we can identify products that are similar in quality, volume, and other characteristics. Our intelligent algorithms then display the closest analogs to the original product, giving you the information you need to make an informed purchase decision.

                      Fudl team

                      OpenAI gymCohere EmbedDALL-E-2

                      Sherlocks Phoenix

                      Our Sherlock's Phoeniks Search Squad solution is a facial recognition system that utilizes generative AI models like ChatGPT and stable diffusion, as well as computer vision techniques, to identify and locate missing persons in real time . The system will take input in the form of text describing the appearance of the missing person, as well as raw images such as sketches, CCTV footage, or blurry photos. The algorithm will then search through internal databases and internet/social media platforms like Facebook and Twitter to find matches and potentially identify the missing person. This system has the potential to significantly aid Police and Investigating agencies in their efforts to locate and bring missing persons home

                      team phoeniks

                      Cohere GenerateChatGPTOpenAI gymStable DiffusionGPT-3

                      AudioQuest

                      Get ready to embark on an epic adventure through sound and story with AudioQuest, the thrilling new text-based adventure game! In AudioQuest, you'll take on the role of a hero on a mission to uncover the secrets of a mysterious and magical world, using nothing but your wits and your trusty set of headphones. With each new stage, you'll be immersed in a rich and detailed soundscape, filled with clues and puzzles that will challenge your mind and test your skills. As you explore this fantastical world, you'll encounter a host of memorable characters, each with their own unique stories and motivations. From fierce dragons to cunning thieves, you'll need to use your intuition and your cunning to navigate the many challenges that lie in your path. With multiple stages to explore, each more challenging than the last, AudioQuest is the perfect way to escape into a world of adventure and excitement. So why wait? Start your journey today and experience the thrill of AudioQuest! AudioQuest uses Whisper to understand what you say and lets you play using the ChatGPT API. We also added SoundCloud API support to include the optimal background music for each situation. We wrapped up everything using a Flask Web Application to bring you the best voice-commanded text-based adventure possible.

                      Hackstreet Boys

                      WhisperChatGPT