Hi HN! Hope you all have a great day. My first ever "product launch" so I am half excited and half nervous. I started learning basic web development (html/css/js) exactly one year ago (first console.log("hello world") on 13 April 2023) and today I am happy to launch a web app - a simple AI tool that writes witty humorous wedding speeches using openAI GPT-4 model. It has been used by some people in a closed group and the feedback was encouraging.
People outside the tech sphere usually don't know how to correctly prompt chatGPT or other LLMs to write something decent. That's the idea behind Toastful. It asks you a series of questions and kind of guides you into providing the necessary information for writing a good speech. The final result is a much better speech that you can confidently deliver in front of people.
I don't have a background in CS so learning all the new tech stuff was really fun. I experimented with fine-tuning GPT-3.5 models as well as a method inspired by RAG to make the output in a specific tone and voice by feeding it sample speeches delivered by people. For now, the RAG inspired method is working satisfactorily but I am constantly playing with the prompts. Meta announced their LLaMa 3 model as well which seems really fast so that is on my list as well.
On the web side, I used NextJS along with Tailwind and Postgres for data persistence. The entire app is hosted on Render ($7/m starter instance).
I would love to get feedback/suggestions from more seasoned devs. My aim is to make this tool a lot better and useful for people.
P.S: The final speech is behind a paywall so if you want to try it for free, you can use FREE100 to bypass the credit card requirement.
People outside the tech sphere usually don't know how to correctly prompt chatGPT or other LLMs to write something decent. That's the idea behind Toastful. It asks you a series of questions and kind of guides you into providing the necessary information for writing a good speech. The final result is a much better speech that you can confidently deliver in front of people.
I don't have a background in CS so learning all the new tech stuff was really fun. I experimented with fine-tuning GPT-3.5 models as well as a method inspired by RAG to make the output in a specific tone and voice by feeding it sample speeches delivered by people. For now, the RAG inspired method is working satisfactorily but I am constantly playing with the prompts. Meta announced their LLaMa 3 model as well which seems really fast so that is on my list as well.
On the web side, I used NextJS along with Tailwind and Postgres for data persistence. The entire app is hosted on Render ($7/m starter instance).
I would love to get feedback/suggestions from more seasoned devs. My aim is to make this tool a lot better and useful for people.
P.S: The final speech is behind a paywall so if you want to try it for free, you can use FREE100 to bypass the credit card requirement.