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

221–230 of 379 posts

Re: Getting AI to write good SQL

#221

Post by mykowebhn »

user3939382 wrote: post #219
mykowebhn wrote: post #199

I understand from a technical POV how this could be considered great news. But I don't see how this is good news at all from a societal POV. The last 15 or so years has seen an unprecedented rise in salaries for engineers, especially software engineers. This has brought an interest in the profession from people who would normally not have considered SW as a profession. I think this is both good and bad. It has brough…

I can’t reconcile statements like this with my experience trying to code with LLMs. As soon as there’s any real complexity they spit out nonsense broken code that in some cases could take a long time to debug. Then when you correct it “You’re totally right, I’ll change it so that x y z”. If you weren’t a senior dev with loads of experience you wouldn’t be able to debug or correct the code these tools produce.

If you were a new dev now learning the ropes, with these AI coding tools available, I highly doubt you would gain the same "loads of experience".

Learning comes through struggle and it's too easy to bypass that struggle now. It's so much easier to get the answers from AI.

Re: Getting AI to write good SQL

#222

Post by Eezee »

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…

I tried it out because of your comment and the very first prompt Gemini 2.5 Pro hallucinated a non-existant plugin including detailed usage instructions.

Not really my idea of good.

Re: Getting AI to write good SQL

#223

Post by conartist6 »

conartist6 wrote: post #210
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…

You don't worry that you can't think anymore without paying google to think for you?

OK, a better scenario than that: for some reason they cut you off. They're a huge company, they don't really care, and you would have no recourse. Many people live this story. Where once you were a programmer, if Google convinces you to eliminate your self-reliance they can then remotely turn off you being a programmer. There are other people who will use those GPU cycles to be programmers! Google will still make money.

Re: Getting AI to write good SQL

#224

Post by christophilus »

petesergeant wrote: post #119
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.

The comments drive me nuts.

// Moved to foo.ts

Ok, great. That’s what git is for.

// Loop over the users array

Ya. I can read code at a CS101 level, thanks.

Re: Getting AI to write good SQL

#225

Post by christophilus »

mykowebhn wrote: post #209
thicTurtlLverXX wrote: post #207

Earlier quoted context omitted.

I understand how, from a technical POV, electricity and electrification could be considered great news. But I don't see how this is good news at all from a societal POV. Think about all the lamplighters who lost their jobs. Streetlights just turn on now? Lamplighting used to be considered a stable job! And what about the ice cutters… For real tho, it's not like there's nothing left to do — we still have potholes to f…

From what I understand, prior to the 1980s/90s lamplighters, waiters, factory workers, etc. could live comfortable lives on decent wages. These days not so much.

From what I understand, life was Dickensian hell for many people. Communism wouldn’t have had much of a chance if everyone was pretty much able to live a decent life as a lamp lighter.

Re: Getting AI to write good SQL

#226

Post by Spivak »

tclancy wrote: post #112
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}}?

I find it funny people are making fun of this while every ORM builds up an object representing the query and then compiles it to SQL. SQL but as a data structure you can manipulate has thousands of implementations because it solves a real problem. This time it's because LLMs have an easier time outputting complex JSON than SQL itself.

Re: Getting AI to write good SQL

#227

Post by christophilus »

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…

A semantic layer would be great. It should be a structured layer designed to make relational queries easy to write. We could call it “structured data language” or maybe “structured query language”.

In all seriousness, I have some complaints about SQL (I think LINQ’s reordering of it is a good idea), but there’s no need to invent another layer on order for LLMs to be able to wrangle it.

Re: Getting AI to write good SQL

#228

Post by b0ringdeveloper »

reacharavindh wrote: post #197
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…

I use Gemini2.5 Pro through work and it is excellent. However, I use Claude 3.7 Sonnet via API for personal use using money added to their account. I couldn’t find a way to use Gemini like a prepaid plan. I ain’t giving my credit card to Google for an LLM that can easily charge me hundreds or thousands of EUR.

Try OpenRouter. Load up with $20 of credits and use their API for a variety of models across providers, including Gemini. I think you pay ~5% extra for the OpenRouter service.

Re: Getting AI to write good SQL

#229

Post by AbstractH24 »

levocardia wrote: post #91

In one of Stephen Boyd's lectures on convex optimization, he has some quip like "if your optimization problem is computationally intractable, you could try really hard to improve the algorithm, or you could just go on vacation for a few weeks and by the time you get back, computers will be fast enough to solve it." I feel like that's actually true now with LLMs -- if some query I write doesn't get one-shotted, I don'…

Has the pace of this slown down or I have just lost track of the narrative?

Feels like innovation in AI is rapidly changing from paradigm-shifting to incremental.

Re: Getting AI to write good SQL

#230

Post by jbeninger »

palmfacehn wrote: post #171
floren wrote: post #138

Earlier quoted context omitted.

Remember, if AI couldn't solve your problem, you were probably using the wrong model. Did you try with o5-selfsuck-20250523-512B?

My least favorite part of this trend is the ageism. "Crusty curmudgeons are not up-to date with the latest bloat if they think RTFM is still a thing", "Oh, you didn't like ORMs? Did you try letting an AI generate code for your ORM?" Maybe in the future all of these assistants will offer something amazing, but in my experience, there is more time invested in prompting that just reading the relevant documentation and h…

As an experienced coder, I find ai invaluable for a ton of stuff, nearly none of it writing production code.

* Variable naming

* Summarizing unfamiliar code

* Producing boilerplate code when I have examples

* Producing one-liners when I've forgotten the parameter order or API specification. I double check, but this is basically a Google that directly answers your question

* Pre-code brainstorming

* Code review. Depending on the language it can catch classes of problems that escape linters

In my experience it won't produce production-ready code, but it's great as a rubber duck and a second pair of eyes.

Post reply on HN