Getting AI to write good SQL • Hacker News Board

Re: Getting AI to write good SQL

#151

Post by harvey9 » Sat, May 17, 2025, 6:50 AM UTC

koakuma-chan wrote: post #96

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…

And Gemini is free.

The first hit is always free

Re: Getting AI to write good SQL

#152

Post by Der_Einzige » Sat, May 17, 2025, 6:50 AM UTC

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…

Shhh!!! Normies will catch on and google will stop making it free.

But more seriously, they need to uncap temperature and allow more samplers if they want to really flex on their competition.

Re: Getting AI to write good SQL

#153

Post by alecco » Sat, May 17, 2025, 7:17 AM UTC

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…

Remember when Microsoft started to do good things? Big corps suck when they are on top and unchallenged. It's imperative to reduce their monopolies.

Re: Getting AI to write good SQL

#154

Post by lifty » Sat, May 17, 2025, 7:22 AM UTC

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…

Excuse my ignorance, but is the good experience somehow influenced by Google AI Studio as well or only by the capability of the model itself? I know Gemini 2.5 is good, have been using it myself for a while. I still switch between Sonnet and Gemini, because I feel Claude code does some things better.

Re: Getting AI to write good SQL

#155

Post by harvey9 » Sat, May 17, 2025, 7:22 AM UTC

deadbabe wrote: post #67

All this LLM written SQL stuff sounds great until you realize if you don’t really know SQL you won’t be able to debug or fix any broken SQL an LLM generates. Thus, this is mainly just a tool for true experts to do less work and still get paid the same, not a tool for beginners to rise to the level of experts.

I'm not an expert but I've written SQL on and off for years. LLMs help me when I can describe my intent but can't think how to implement it. I don't expect a perfect solution just a starting point that I can refine.

Re: Getting AI to write good SQL

#156

Post by meindnoch » Sat, May 17, 2025, 7:23 AM UTC

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

^ kids, this is what AI-induced brainrot looks like.

Re: Getting AI to write good SQL

#157

Post by th0ma5 » Sat, May 17, 2025, 7:28 AM UTC

insin wrote: post #93

Is it too late to rescue the phrase "one-shotted" or is it already too far gone, like "AI" and "agent"?

Reminds me the "crypto" name overloading. It is clear that fanboys are jealous of competence.

Re: Getting AI to write good SQL

#158

Post by JodieBenitez » Sat, May 17, 2025, 7:30 AM UTC

Wait... people need AI to write SQL ?

Re: Getting AI to write good SQL

#159

Post by iddan » Sat, May 17, 2025, 7:46 AM UTC

For anybody wanting to use best-in-class AI SQL, I highly recommend checking out Sherloq (W23): https://www.sherloqdata.io/

Re: Getting AI to write good SQL

#160

Post by nativeit » Sat, May 17, 2025, 7:46 AM UTC

koakuma-chan wrote: post #96

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…

And Gemini is free.

We’re all paying for this. In this case, the costs are only abstract, rather than the competing subscription options that are indeed quite tangible _and_ abstract.