←back to thread

Getting AI to write good SQL

(cloud.google.com)
476 points richards | 1 comments | 16 May 25 21:10 UTC | HN request time: 0.205s | source
Show context
rectang ◴[17 May 25 00:04 UTC] No.44010899[source]▶
> We will cover state-of-the-art [...] how we approach techniques that allows the system to offer virtually certified correct answers.

I don't need AI to generate perfect SQL, because I am never going to trust the output enough to copy/paste it — the risk of subtle semantic errors is too high, even if the code validates.

Instead, I find it helpful for AI to suggest approaches — after which I will manually craft the SQL, starting from scratch.

replies(4): >>44011204 #>>44011349 #>>44011379 #>>44011432 #
hsbauauvhabzb ◴[17 May 25 01:36 UTC] No.44011379[source]▶
Explain that to the average manager or junior engineer, both who don’t care about your desire to build well but not fast.
replies(2): >>44011448 #>>44011772 #
noosphr ◴[17 May 25 01:51 UTC] No.44011448[source]▶
> So now that we brought down prod for a day the new rule is no AI sql without three humans signing off on any queries.
replies(1): >>44011475 #
Closi ◴[17 May 25 01:57 UTC] No.44011475[source]▶
If that’s the scenario, I would be asking why the testing pipeline didn’t catch this rather than why was the AI SQL wrong.
replies(3): >>44011595 #>>44011821 #>>44014227 #
1. dns_snek ◴[17 May 25 13:35 UTC] No.44014227[source]▶
To offer a 3rd option - what testing pipeline? Incompetent managers aren't going to approve of developers "wasting their time" on writing high quality tests.