News for hackers. Stuff that matters.

A comment on Getting AI to write good SQL. Parent comment

Re:Getting AI to write good SQL by noosphr on Friday May 16, 2025 @09:51PM (#44011448)
> 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.
[ Parent | on HN ]
Re:Getting AI to write good SQL by Closi on Friday May 16, 2025 @09:57PM (#44011475)
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.
[ Parent | on HN ]
Re:Getting AI to write good SQL by noosphr on Friday May 16, 2025 @10:31PM (#44011595)
Because the testing pipeline isn't the real database.

Anyone that knows a database well can bring it down with a innocent looking statement that no one else will blink at.

[ Parent | on HN ]
Re:Getting AI to write good SQL by Closi on Sunday May 18, 2025 @05:06AM (#44020014)
Sure, but everyone knows humans end up bringing down the database too by writing an innocent looking test query nobody else blinks at, which is why you end up needing a testing strategy for ANY SQL before YOLO'ing into prod.
[ Parent | on HN ]
Re:Getting AI to write good SQL by fkyimeanit on Friday May 16, 2025 @11:28PM (#44011821)
Because the testing pipeline was generated by AI, and code-reviewed by AI, reading a PR description generated by AI.
[ Parent | on HN ]
Re:Getting AI to write good SQL by dns_snek on Saturday May 17, 2025 @09:35AM (#44014227)
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.
[ Parent | on HN ]