I’ve used it generate about 10 scripts that did some combination of json/yaml data wrangling and AWS automation using the AWS SDK in Python. It’s been correct around 90%+ of the time.
Criticizing ChatGPT for getting one line wrong that a human who hasn’t programmed in the same language in over 30 years would also get wrong (I happened to remember the technique from reading it in the back of a magazine in the 80s) and then being able to use it to iterate is like criticizing a monkey who song the national anthem because one note was off key?
How is mashing code together any different than the average human does?
I have also asked it to generated AWS related code in Python and it has something wrong every single time.
Its incrementally better than just copy & pasting from StackOverflow, since it will customize the code for you, but if you try to go beyond what can easily be found on StackOverflow it will fail you.
Criticizing ChatGPT for getting one line wrong that a human who hasn’t programmed in the same language in over 30 years would also get wrong (I happened to remember the technique from reading it in the back of a magazine in the 80s) and then being able to use it to iterate is like criticizing a monkey who song the national anthem because one note was off key?
How is mashing code together any different than the average human does?