GPT Pilot can code out the entire app as you oversee the code being written. This is our try to see how can GPT-4 be utilized to generate working apps and to our surprise, it works quite well.
Very impressive!
I knew what Zvonimir and the team were working on and was still floored when I saw the demo.
The ability to basically write a tech spec from user requirements, then plan the project and then execute it step by step is a game changer, and a definitive difference from other "code-with-ai" tools out there.
I also like that it shows you exactly what it's doing along the way (so you know why it does what it does), and that it asks you to allow it to run commands (I'm wary of just giving some AI full control of my terminal).
Amazing work so far, looking forward to using this and seeing you grow the product!
Conceptually very interesting approach based on what experienced software developers know by their heart: test-driven development is the fastest way to develop high-quality software. GPT Pilot is a tool that automates such a process resulting in high-quality code at a fraction of the time and cost invested.
I'm genuinely impressed with GPT Pilot! After trying it out, I can't help but feel excited about its future developments and where it's headed.
Regarding the underlying LLMs, are they fixed, or do users have the option to choose between different models, such as ChatGPT3.5, ChatGPT4, or LLAMA?
