2 years of experience
I'm a 2nd-year Computer Science undergrad at The University of Tokyo. I build stuff around React and Flutter.
Extracting information from a large database can be difficult, especially when you don't know what to look for. That's exactly why ChatGPT and friends were born to assist Google. However, these models are not to be used for personal data. Sometimes, you just want to know what you did last week, or last year. Sometimes, you just want to know what kind of person you were. And, sometimes you want a deep analysis on your thought and past. Here is how Memoiz works. First, you have your primary database. This is where you store all your text data. Then, you might have a secondary database. This is where you store the embeddings of your text data. (It is possible that both can be on Redis Stack) When the text data is "archived", its content will be embedded by Cohere Embed, turning into a (seemingly but not) meaningless 4096-dimension vector saved into the Redis server. When the user starts chatting with Memoiz, the chat history will determine the keywords for semantic search on the Redis server. The closest vectors will be treated as a context for the text generation prompt. The text generation prompt will then be sent to the Cohere Generate model for the chat response. In the next steps, we plan to develop a larger-scale mood tracker with a more powerful language model. We also plan to share a public API for developers to use Memoiz in their own projects.
Phone-call anxiety is not uncommon, and chances are that you don't want to pick up unknown phone calls too. At the same cost of regular phone calls (~$0.02/min), you can clone yourself and let it do the mundane task of picking up the calls. To be honest, having Call'em pick up awkward phone calls is undermining the true power of ElevenLabs. We (I, haha) are planning to expand the possibility of Call'em to be usable by everyone. Making a dinner reservation? Call'em. Expecting a call from your son's teacher? Call'em. Dealing a $100-million business? Well, you can still Call'em, but you can also manage the control flow, set up a customer relationship system, and direct the call to yourself as soon as you're available. Imagine customers losing their interest because you were busy in a call with another customer. Pfft, couldn't be me; I'd just Call'em.
Success in business doesn't always require a brand-new idea. After all, Google wasn't the pioneer of search engines, and Facebook didn't invent social networking. The key to success lies in learning from those who've already achieved it and steering clear of the pitfalls that others have stumbled into. That's the whole idea of Revamp. We employed Cohere newest tool, Coral, to create an agent capable of retrieving real-world competitors' data and see where we stand among them. First, we look into the 4 P's in marketing (Product, Price, Place, Promotion) which uses the connector mode and then conduct a SWOT analysis based on the 4 P's result which uses the document mode. Finally, we generate "new" business ideas based on strengths, weaknesses, opportunities, and threats of our competitors. Now your idea is well-validated, and you can start working today.
Join us for a hackathon where we will be using OpenAI Whisper to create innovative solutions! Whisper is a neural net that has been trained to approach human level robustness and accuracy for English speech recognition. We will be using this tool to create applications that can transcribe in multiple languages, as well as translate from those languages into English. This will be a great opportunity for you to learn more about speech processing and to create some useful applications!
🛠️ 7 days of Learning and Building 🤝 Come with your team or find one during the Hackathon 🦾 Free access to Generative AI models and Tech Tutorials 🏅 Win a place in the Early Stage StartUp Accelerator program 🚀 Join community of AI experts