←back to thread

Getting AI to write good SQL

(cloud.google.com)
478 points richards | 5 comments | 16 May 25 21:10 UTC | HN request time: 0.675s | source
Show context
zeroq ◴[17 May 25 03:04 UTC] No.44011740[source]▶
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?)
replies(2): >>44012230 #>>44012287 #
e3bc54b2 ◴[17 May 25 05:24 UTC] No.44012230[source]▶
The worse part is not even being trolled at AI roundabout. The worse part is gaslighting by people who then go on to imply that I'm dumb to not be able to 'guide' the model 'towards the solution', whatever the fuck that means. And this is after telling me that model is so smart to just know what I want.

Claude and Gemini are pretty decent at providing a small and tight function definition with well defined parameters and output, but anything big and it starts losing shit left and right.

All vibecoding sessions I've seen have been pretty dead easy stuff with lot of boilerplate, maybe I'm weird for just not writing a lot of boilerplate and rely on well-built expressive abstractions..

replies(2): >>44012291 #>>44012733 #
1. floren ◴[17 May 25 05:46 UTC] No.44012291[source]▶
Remember, if AI couldn't solve your problem, you were probably using the wrong model. Did you try with o5-selfsuck-20250523-512B?
replies(3): >>44012376 #>>44012767 #>>44012865 #
2. kubb ◴[17 May 25 06:17 UTC] No.44012376[source]▶
It’s brilliant because you can always shift the blame on the user. Wrong prompt, wrong model, should have used an agent and ran 3 models in parallel, etc.

Meanwhile we get claims that the tools are as capable as a junior programmer, and CEOs believe that.

3. sensanaty ◴[17 May 25 07:54 UTC] No.44012767[source]▶
Yeah it's my favourite argument. Apparently this magical tool that can replace engineers and can do and write anything needs you to write prompts so detailed that you could have just written the damn code yourself, and probably had an easier time with it to boot.

The whole thing feels like we're in a collective delusion because idiotic managers and C-suites are blindly lapping up the advertising slop coming from the AI companies.

4. palmfacehn ◴[17 May 25 08:20 UTC] No.44012865[source]▶
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 having a coherent design.

My suspicion is that many, (but not all please no flames) of the biggest boosters of AI coding are simply inexperienced. If this is true, it makes sense that they wouldn't recognize the numerous foot-guns in AI generated code.

replies(1): >>44013803 #
5. jbeninger ◴[17 May 25 12:30 UTC] No.44013803[source]▶
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.