←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: 0.434s | source
Show context
hakanito ◴[17 May 25 07:58 UTC] No.44012780[source]▶
The game changer for me will be when AI stops hallucinating SDK methods. I often find myself asking ”show me how to do advanced concept X in somewhat niche Y sdk”, and while it produces confident answers, 90% of the time it is suggesting SDK methods that do not exist, so a lot of time is wasted just arguing about that
replies(4): >>44012808 #>>44012853 #>>44013192 #>>44016229 #
M4v3R ◴[17 May 25 08:03 UTC] No.44012808[source]▶
The current method of solving this is providing the AI with the documentation of the SDKs your code uses. Current LLMs have quite big context windows so you can feed them a lot of documentation. Some tools can even crawl multipage documentation and index them for the use of LLMs.
replies(1): >>44012939 #
hakanito ◴[17 May 25 08:39 UTC] No.44012939[source]▶
How do you do that practically/reliably? Would be great to just paste a link to the SDK Github repo, but doesn't seem to work (yet) in my experience
replies(3): >>44012975 #>>44014001 #>>44018212 #
1. jstummbillig ◴[17 May 25 08:51 UTC] No.44012975[source]▶
Simple way would be to use either Sonnet 3.7/5 or Gemini 2.5 pro in windsurf/cursor/aider and tell it to search the web, when you know an SDK is problematic (usually because it's new and not in the training set).

That's all it takes to get reliably excellent results. It's not perfect, but, at this point, 90% hallucinations on normal SDK usage strongly suggests poor usage of what is the current state of the art.