Using Amazon CodeWhisperer to write Hugging Face code
October 28, 2022
Following my test of Github Copilot (https://youtu.be/HxyG896swQU), I was curious how Amazon CodeWhisperer would perform on the same example. So I gave it a try!
⭐️⭐️⭐️ Don't forget to subscribe to be notified of future videos ⭐️⭐️⭐️
In a nutshell, things didn't go well :-/ I found the service slow, and most of the prompts it generated were irrelevant. It also struggled to keep generating additional lines of code. Failing to trigger on copy-pasted prompted was very annoying (probably an issue with the AWS extension for VS Code).
Unlike Copilot, I wouldn't use CodeWhisperer to get real work done. The service is still in preview at the time of recording, and one can only hope that it will get much better over time. I'll give another try when it becomes generally available.
Getting started :
- Hugging Face: https://huggingface.co/course
- Amazon CodeWhisperer: https://aws.amazon.com/codewhisperer/
And if you're interested in LLMs for code generation, check out the BigCode project at https://www.bigcode-project.org/
Transcript
Music
So, Music
Bye. Music
Music
So, Music
Music
Music
Music
Music
Music
Music
Music
Music
Music
Music
Music
Music
Music
Music
Music
Music
Music
Music
Music
Music
Music
Music
Music
Music
Music
Music
Music
Music
Music
Music
Music
Music
Music
The End
Music
The next step is to make a difference between the two. Music
you