Python Testing Showdown: Gemini 1.5 Pro Vs GPT o1-Preview

In this video, we run a side-by-side test of two advanced AI models: GPT-4.0 Preview and Gemini 1.5 Pro 002. The task for both models is to generate a Python script that builds a 25-key piano keyboard using a graphical user interface (GUI), complete with mouse interaction and sound playback. The goal of this test is to determine which model can generate a fully functioning script that produces no terminal errors in the fewest tries.
Prompt Used:
Here is the specific prompt that was given to each model:
Please generate a Python script that creates a graphical user interface (GUI) with the following features:
Display a visual representation of a 25-key piano keyboard.
The keys should be arranged in the standard piano layout, with white and black keys.
The keyboard should be centered around middle C (C4).
Each key should correspond to the correct musical pitch it represents on a real piano.
Mouse interaction:
When a user clicks on a key with the mouse, it should trigger a 'key press' event.
The pressed key should change appearance (e.g., change color) to indicate it's being played.
Audio playback:
When a key is pressed, play the corresponding piano note sound.
Use an appropriate audio library (e.g., pygame.mixer, simpleaudio) to handle sound playback.
Ensure that the pitch of each note matches its corresponding key on a real piano.
The frequency range should span from the A below middle C (A3) to the A two octaves above middle C (A5).
Include error handling for potential issues like missing audio files or GUI errors.
Add comments to explain key parts of the code for better understanding.
Optional Enhancements (if time allows):
Implement key release detection to stop the sound when the mouse button is released.
Add volume control for the audio playback.
Include an option to switch between different piano sound samples or synthesized tones.
The video then explores the results.
This experiment highlights the comparative strengths and areas for improvement in the respective AI models, giving a deeper insight into their abilities in real-world coding tasks.

[@drmarioschannel]

have you coded advance voice into your chat robots? i guess it would need an api

[@OminousIndustries]

I have not done that. They use MS Azure for speech and I have noticed some of the newer azure voices are a bit more "emotive", but not on the level of advanced voice mode. I am blown away by what I experienced with advanced voice so far.