AI Agents for scraping. With agents able to run code safely now, I wanted to test their abilities to scrape data from websites without specifying any input requirements such as elements or classes. The result is shockingly good, considering I spent less than 4 hours doing it.
The challenge I didn’t want to use a fully-fledged agent framework; I wanted to write one agent that would give feedback to itself if there were any errors to learn and iterate.
After launching Job Description AI - Professional job description generator with few clicks on Product Hunt, I spent the following three weeks fixing bugs and adding features requested by users to improve the service.
I have created a notion page for releases and included a link inside the portal to present the progress to regular users, but how do I inform everyone?
I decided to send my first email update to all registered users informing them about the progress in the last three weeks.
I have received my invitation to OpenAI around mid December and started playing with API a week after. In this blog post, I will list the top 10 things I didn’t know or didn’t expect as a newcomer to the GPT-3. The context is aimed for developers but most of the the information is still relevant for non developers too.
TL;DR If you don’t like details, here is a TL;DR: