Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Getting AI to write good SQL

cloud.google.com

Post reply on HN
Print view View original

101–110 of 379 posts

Re: Getting AI to write good SQL

#101

Post by fooker »

RadiozRadioz wrote: post #22
nashashmi wrote: post #12

AI text to regex solutions would be incredibly handy.

This comment appears frequently and always surprises me. Do people just... not know regex? It seems so foreign to me. It's not like it's some obscure thing, it's absolutely ubiquitous. Relatively speaking it's not very complicated, it's widely documented, has vast learning resources, and has some of the best ROI of any DSL. It's funny to joke that it looks like line noise, but really, there is not a lot to learn to u…

Regex, especially non standard (and non regular) extensions can be pretty tricky to grok.

http://alf.nu/RegexGolf?world=regex&level=r00

Re: Getting AI to write good SQL

#102

Post by noosphr »

Closi wrote: post #87
noosphr wrote: post #86

Earlier quoted context omitted.

> 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.

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.

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.

Re: Getting AI to write good SQL

#103

Post by andndnndd »

ljm wrote: post #13
mritchie712 wrote: post #2

the short answer: use a semantic layer. It's the cleanest way to give the right context and the best place to pull a human in the loop. A human can validate and create all important metrics (e.g. what does "monthly active users" really mean) then an LLM can use that metric definition whenever asked for MAU. With a semantic layer, you get the added benefit of writing queries in JSON instead of raw SQL. LLM's are much…

> you get the added benefit of writing queries in JSON instead of raw SQL. I’m sorry, I can’t. The tail is wagging the dog. dang, can you delete my account and scrub my history? I’m serious.

[flagged]

Re: Getting AI to write good SQL

#104

Post by IncreasePosts »

ljm wrote: post #13
mritchie712 wrote: post #2

the short answer: use a semantic layer. It's the cleanest way to give the right context and the best place to pull a human in the loop. A human can validate and create all important metrics (e.g. what does "monthly active users" really mean) then an LLM can use that metric definition whenever asked for MAU. With a semantic layer, you get the added benefit of writing queries in JSON instead of raw SQL. LLM's are much…

> you get the added benefit of writing queries in JSON instead of raw SQL. I’m sorry, I can’t. The tail is wagging the dog. dang, can you delete my account and scrub my history? I’m serious.

You're right, it's a bit ridiculous. This is a perfect time to use xml instead of json.

Re: Getting AI to write good SQL

#106

Post by wheelerwj »

treebeard901 wrote: post #105

If a lot of the value in a company is the software and over time a handful of AI companies start writing all the software, who really ends up owning all the value of the company?

That’s easy. None of the value is in the software. The only value is in customers that use the software.

Re: Getting AI to write good SQL

#109

Post by rectang »

paulddraper wrote: post #83
rectang wrote: post #35

> 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 S…

Hopefully your trust in yourself is warranted

I embrace my fallibility, and enthusiastically pursue testing, code reviews, staging environments, and so on to minimize the mistakes that make it through to production.

It seems to me that this skeptical mindset is consonant with handling AI output with care.

Re: Getting AI to write good SQL

#110

Post by zeroq »

Every once in a while I've been trying AI, since everyone and their mother told me to, so I comply.

My recent endevour was with Gemini 2.5:

  - Write me a simple todo app on cloudflare with auth0 authentication.
  - Here's a simple todo on cloudflare. We import the @auth0-cloudflare and...
  - Does that @auth0-cloudflare exists?
  - Oh, it doesn't. I can give you a walkthrough on how to set up an account on auth0. Would you like me to?
  - Yes, please.
  - Here. I'm going to write the walkthrough in a document... (proceed to create an empty document)
  - That seems to be an empty document.
  - Oh, my bad. I'll produce it once more. (proceed to create another empty document)
  - Seems like you're md parsing library is broken, can you write it in chat instead?
  - Yes... (your gemini trial has expired, would you like to pay $100 to continue?)
Post reply on HN