←back to thread

Getting AI to write good SQL

(cloud.google.com)
478 points richards | 1 comments | 16 May 25 21:10 UTC | HN request time: 0.001s | source
Show context
mousetree ◴[16 May 25 22:02 UTC] No.44010169[source]▶
Out of all the AI tools and models I’ve tried, the most disappointing is the Gemini built into BigQuery. Despite having well named columns with good descriptions it consistently gets nowhere close to solving the problem.
replies(2): >>44010326 #>>44010346 #
flysand7 ◴[16 May 25 22:31 UTC] No.44010346[source]▶
Having written more SQL than any other programming language by now, every time I've tried to use AI to write the query for me, I'd spend way more time getting the output right than if I'd just written it myself.

As a quick aside there's one thing I wish SQL had that would make writing queries so much faster. At work we're using a DSL that has one operator that automatically generates joins from foreign key columns, just like

    credit.CLIENT->NAME
And you got clients table automatically joined into the query. Having to write ten to twenty joins for every query is by far the worst thing, everything else about writing SQL is not that bad.
replies(6): >>44010730 #>>44010752 #>>44011084 #>>44011577 #>>44015959 #>>44020501 #
1. galenmarchetti ◴[17 May 25 00:36 UTC] No.44011084[source]▶
yeah we’re doing something similar under the hood at AstroBee. it’s way way way easier to handle joins this way.

imo any hope of really leveraging llms in this context needs this + human review on additions to a shared ontology/semantic layer so most of the nuanced stuff is expressed simply and reviewed by engineering before business goes wild with it