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

111–120 of 379 posts

Re: Getting AI to write good SQL

#111

Post by rectang »

hsbauauvhabzb wrote: post #80
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…

Explain that to the average manager or junior engineer, both who don’t care about your desire to build well but not fast.

It’s not true that I want to build “well but not fast” — I’m trying to add value, and both speed and reliability matter. My productivity is high and I don’t have trouble articulating why; my approach has generally (though not universally) been well received by management and colleagues.

Re: Getting AI to write good SQL

#112

Post by tclancy »

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…

Mother of God. I can write JSON instead of a language designed for querying. What is the advantage? If I’m going to move up an abstraction layer, why not give me natural language? Lots of things turn a limited natural language grammar into SQL for you. What is JSON going to {do: for: {me}}?

Re: Getting AI to write good SQL

#113

Post by fkyimeanit »

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

You should have written your comment in JSON instead of raw English.

Re: Getting AI to write good SQL

#114

Post by yujzgzc »

wewewedxfgdf wrote: post #42
CuriouslyC wrote: post #39

Earlier quoted context omitted.

I'm really surprised more people haven't caught on. Claude can one shot small stuff of similar complexity, but as soon as you start to really push the model into longer, more involved use cases Gemini pulls way ahead. The context handling is so impressive, in addition to using it for coding agents, I use Gemini as a beta reader for a fairly long manuscript (~85k words) and it absolutely nails it, providing a high lev…

It is absolutely the greatest golden age in programming ever - all these infinitely wealthy companies spending bajillions competing on who can make the best programming companion. Apart from the apologising. It's silly when the AI apologises with ever more sincere apologies. There should be no apologies from AIs.

You're absolutely right! My mistake. I'll be careful about apologizing too much in the future.

Re: Getting AI to write good SQL

#115

Post by fkyimeanit »

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 was generated by AI, and code-reviewed by AI, reading a PR description generated by AI.

Re: Getting AI to write good SQL

#116

Post by icedchai »

emmelaich wrote: post #99
flysand7 wrote: post #11

Earlier quoted context omitted.

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, j…

I'd like there to be a function or macro for a bunch of joins, say DEFINE products_by_order AS orders o JOIN order_items oi ON o.order_id = oi.order_id JOIN products p ON oi.product_id = p.product_id You could make it visible to the DB rather than just a macro so it could optimise it by caching etc. Sort of like a view but on demand.

Sounds like a CTE?

Re: Getting AI to write good SQL

#117

Post by fkyimeanit »

nashashmi wrote: post #12

AI text to regex solutions would be incredibly handy.

"Text to SQL", "text to regex", "text to shell", etc. will never fundamentally work because the reason we have computer languages is to express specific requirements with no ambiguity.

With an AI prompt you'll have to do the same thing, just more verbosely.

You will have to do what every programmer hates, write a full formal specification in English.

Re: Getting AI to write good SQL

#119

Post by petesergeant »

wewewedxfgdf wrote: post #26

Can I just say that Google AI Studio with latest Gemini is stunningly, amazingly, game changingly impressive. It leaves Claude and ChatGPT's coding looking like they are from a different century. It's hard to believe these changes are coming in factors of weeks and months. Last month i could not believe how good Claude is. Today I'm not sure how I could continue programming without Google Gemini in my toolkit. Gemini…

Is this distinct from using Gemini 2.5 Pro? If not, this doesn’t match my experience — I’ve been getting a lot of poorly designed TypeScript with an excess of very low quality comments.

Re: Getting AI to write good SQL

#120

Post by alostpuppy »

wewewedxfgdf wrote: post #26

Can I just say that Google AI Studio with latest Gemini is stunningly, amazingly, game changingly impressive. It leaves Claude and ChatGPT's coding looking like they are from a different century. It's hard to believe these changes are coming in factors of weeks and months. Last month i could not believe how good Claude is. Today I'm not sure how I could continue programming without Google Gemini in my toolkit. Gemini…

How do you use it exactly? Does it integrate with any IDEs?
Post reply on HN