How does bison-001 compare to GPT4 or Github copilot?

Short Course Q&A Pair Programming with a Large Language Model
1

Hi, this was a clear and interesting course.
However, I found the example where the LLM tried to find the bug in the code and write code to fix it showed that the model didn’t fully understand the problem. Even though it suggested a function where the bug was, its solution was not correct.

I am curious how GPT4 / Bing / Github copilot chat would do with this exact example?

Also I am sad that I can’t seem to get a PALM api key here in Canada, I assume it’s not available in Canada yet?

Thanks,
Geoff

2 Likes