We tested Bard (aka Bison in GCP) for generating SQL. It has worse generalizatio...

zainhoda on Sept 19, 2023 | parent | context | favorite | on: Ask HN: 6 months later. How is Bard doing?

We tested Bard (aka Bison in GCP) for generating SQL.

It has worse generalization capabilities than even GPT-3.5 but actually does as well at GPT-4 when given contextually relevant examples selected from a large corpus of examples.

https://vanna.ai/blog/ai-sql-accuracy.html

This suggests to me that it needs longer prompts to avoid the hallucination problem that everyone else seems be experiencing.

kromem on Sept 20, 2023 [–]

That does kind of sound like there was less specialized fine tuning and the in context learning is doing the heavy lifting.