For example, I asked 3.5 to find a bug in a lengthy piece of Javascript. It said it's hard to give a correct answer because it doesn't know what the HTML or CSS looks like.
GPT4 spotted the bug almost immediately (it didn't manage to fix it though).
With GPT 3.5 and 4, I was able to just paste in the error and it'd do the rest. Bard however tried to tell me what the error could be, and wouldn't do well even when asked to fix the code.
Even GPT 4 though, when asked to go from specs to tests + code, would get stuck in a loop of making one test pass only to make the other pass and vice versa. The program I tried to let it write was a query validator that can test whether a string matches a pattern that uses AND, OR and NOT.
It did well on parsing my specs into tests, but from there on it didn't go very well.