Hacker News Reader

One area where I noticed Bard was clearly behind (at least without crafting a better prompt) is getting from half-working program to a running program then sometime even to a correct program (I was using Python).

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.

Bard uses PaLM 2 now, which is definitely better than GPT-3.5. The question is only whether it is better than GPT-4.

What is its training data cutoff date?

We don't know (both for previous model LaMDA and new model PaLM 2), but it is less important for Bard because Bard has access to live data from Google search.