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

231–240 of 379 posts

Re: Getting AI to write good SQL

#231

Post by cmrdporcupine »

christophilus wrote: post #227
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.

The semantic layer for database queries is (roughly) the relational algebra.

Re: Getting AI to write good SQL

#232

Post by AbstractH24 »

zkry wrote: post #205
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…

Im curious why there's this sentiment in regarding advances in AI. High level programming languages didnt in the least bit take away the value of the SW profession, despite allowing a vast number more people to write software. The amount and complexity of software will expand to its very outer bounds for which specialists will be required.

A better comparison I think is low-code platforms.

There are plenty of folks making a living using platforms like Salesforce and “clicks not code,” but it never led to an implosion of the SE job market. Just expanded the tech job pool. And it’s hard to imagine how that would have happened if everything needed to be coded.

Like how a growth in medical-paraprofessionals didn’t negate the need for doctors and nurses.

Re: Getting AI to write good SQL

#233

Post by kdmtctl »

alostpuppy wrote: post #120
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?

Copilot has it in preview. I found it looks deeper on devops tasks in the Agent mode. But context matters, you should include everything and it will push. Now I switch between Cloude and Gemini when one of them starts going circles. Gemini certainly could have more context but Copilot clearly limits it. Didn't try with Studio key though, only default settings.

Re: Getting AI to write good SQL

#234

Post by Agraillo »

mritchie712 wrote: post #211
ljm wrote: post #13

Earlier quoted context omitted.

> 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.

LLMs are far more reliable at producing something like this: { "dimensions": [ "users.state", "users.city", "orders.status" ], "measures": [ "orders.count" ], "filters": [ { "member": "users.state", "operator": "notEquals", "values": ["us-wa"] } ], "timeDimensions": [ { "dimension": "orders.created_at", "dateRange": ["2020-01-01", "2021-01-01"] } ], "limit": 10 } than this: SELECT users.state, users.city, orders.stat…

The programming languages are more predictable than human. So the rules are much easier to be "compressed" after they're basically detected when fed with big data. Your two examples imho are easily interchangeable during follow-up conversation with a decent LLM. Tested this with the following prompt and fed a c fragment and an SQL-fragment, got in both cases something like your first one

> Please convert the following fragment of a programming language (auto-detect) into a json-like parsing information when language construct is represented like an object, fixed branches are represented like properties and iterative clauses (statement list for example) as array.

Re: Getting AI to write good SQL

#235

Post by priceofmemory »

CuriouslyC wrote: post #204
snthpy wrote: post #196

Earlier quoted context omitted.

I also used it to "vibe write" a short story. I use it similarly to vibe coding, I give the theme and structure of the story along with the major sections and tensions and conflicts I want to express and then it filled in the words in my chosen style. I also created an editor persona and then we went back and forth between the editor and writer personas to refine the story. The Omega Directive: https://snth.prose.sh/…

My writing process is a bit different from my coding process with AI, it's more of an iterative refinement process. I tend to form the story arc in my head, and outline the major events in a timeline, and create very short summaries of important scenes, then use AI to turn those summaries into rough narrative outlines by asking me questions and then using my answers to fill in the details. Next I'll feed that abbrevi…

That sounds very similar to my AI vibe writing process. Start with chapter outlines, then ask AI to fill in the details for each scene. Then ask AI to point out any plot holes or areas for improvement in the chapter (with relation to other chapters). Then go through chapter by chapter for a second rewrite doing the same thing. At ~100k words for a fan-fiction novel but expect to be at about 120k words after this latest rewrite.

https://frypatch.github.io/The-Price-of-Remembering/

Re: Getting AI to write good SQL

#236

Post by the_arun »

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…

Are you talking about Firebase Studio?

Re: Getting AI to write good SQL

#237

Post by cloudking »

galenmarchetti wrote: post #51
cloudking wrote: post #4

This is pretty simple in any foundation model, provide a well commented schema and ask for the query

there’s two kinds of people using AI to generate SQL…those who say it’s already solved and those who say it’ll be impossible to ever solve

Yep, probably why I got upvoted then downvoted. I've been using LLMs to write SQL queries for 2 years.

Re: Getting AI to write good SQL

#238

Post by owebmaster »

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'…

> I just shelve it 'til next month and the next big OpenAI/Anthropic/Google model will usually crush it.

1 month to write some code with LLM, that's quite the opposite of the promised productivity gain

Re: Getting AI to write good SQL

#239

Post by theropost »

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.

I wish my AI would tell me when I'm going in the wrong direction, instead of just placating my stupid request over and over until I realize.. even though it probably could have suggested a smarter direction, but instead just told me "Great idea! "

Re: Getting AI to write good SQL

#240

Post by gizmodo59 »

fourfun wrote: post #131

Google may be getting AI to write good SQL, but they aren’t getting it to write good blog posts.

The blog post lacks lots of details and sounds more of a marketing piece and “Try this!”. They did not release the evals, a very basic architecture flow which is not novel nor any real world benchmarks that says how it worked expect some vague statements. Must have been generated by Gemini
Post reply on HN