🗓️ This 7-day virtual hackathon from January 27 to February 3 will be your time to shine!
💻 Construct AI apps with the latest LLM-powered technology from Cohere and try the newly released Multilingual Text Understanding model
✔️ There's no prerequisite level. Just starting out with AI? Or perhaps you're a veteran Data Scientist? A Designer? A Business Developer? We want you and your domain expertise!
🐱‍💻 Sign up now for free and let's get going!

Cohere Hackathon

🛠️ Build your MVP in 7 days
🤝 Find your team on the platform
📈 Hours of educational context
🦾 Generative AI tools to build with
🏅 Further support for winners

AI Startup Hackathon

No-rank

Apprentice

Tamás Takács

Are you tired of endlessly scrolling through pages of champions in League of Legends, trying to find the perfect fit for your playstyle? 
Look no further! Co:mpass is here to introduce an innovative solution that will change the way you choose your champions forever. With a simple prompt text, our application will recommend the best champions for you, based on your preferences for playstyle and strategy. 
Imagine having the perfect champion recommended to you, every time you play. No more guesswork, no more hesitation,  just pure gaming bliss.
Get ready to experience the future of champion selection, with our cutting-edge application!

Compass

Scrummy provides an easy way to manage client requests. The client sends the requests, bug reports or feature request via email to the support email. Scrummy detects that a new email is in the inbox. It creates a summary of the email from the client and sends a confirmation email back to the client to verify if it understands the problem correctly. It provides two choices so the client can choose which one describes the issue better. Then, by clicking the corresponding link Scrummy will create a ticket in Trello about the selected description. Then the development team can extend the ticket during a grooming.

Scrummy

One of the best AI labs in the world. By using the Cohere platform we are able to use one of the best and most powerful language models for our own! There are many tutorials, including our own one, that show how to use Cohere.

Cohere

GPT-3 stands for Generative Pre-trained Transformer 3 and it is an autoregressive language model that uses deep learning to produce human-like text. It is the third-generation language prediction model in the GPT-n series created by OpenAI. GPT-3 is currently in open beta.

GPT-3

OpenAI Codex is an artificial intelligence platform that enables developers to translate natural language into code. 

Codex

DALL·E 2 is a new AI system that can create realistic images and art from a description in natural language.

DALL-E-2

AI21 Labs is a platform for building AI applications. It provides a suite of tools and guides for building AI applications and training models. AI21 Labs helps developers and businesses use cutting-edge language models, with no NLP expertise required. Access powerful language models using an API that makes you smile

AI21 Labs

Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification.

Whisper

YOLOv7 is the new state-of-the-art object detector in the YOLO family. According to the paper, it is the  most accurate and fastest real-time object detection to date.

YOLOv7

ChatGPT is a large language model trained by OpenAI to generate human-like text in a conversational style. It is a variant of the GPT-3 model, which was specifically designed to be used to generate text in response to user input. The ChatGPT model has been trained on a vast amount of text data, including conversations and other types of human-generated text, which allows it to generate text that is similar in style and content to human conversation. ChatGPT can be used to generate responses to questions, code, make suggestions, or provide information in a conversational manner, and it is able to do so in a way that is often indistinguishable from human-generated text. The initial model has been trained using Reinforcement Learning from Human Feedback (RLHF), using methods similar to InstructGPT, but with slight differences in the data collection setup. The model is trained using supervised fine-tuning, where human AI trainers provided conversations in which they played both sides—the user and an AI assistant. The trainers would have had access to model-written suggestions to help them compose their responses.

Tamas Takacs@tams_takcs104

🤓 Submissions

Compass

Scrummy

📝 Certificates

Cohere Hackathon | Certificate

AI Startup Hackathon | Certificate