Most active commenters

    ←back to thread

    Getting AI to write good SQL

    (cloud.google.com)
    477 points richards | 21 comments | | HN request time: 2.192s | source | bottom
    Show context
    wewewedxfgdf ◴[] No.44010757[source]
    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 AI Studio is such a giant leap ahead in programming I have to pinch myself when I'm using it.

    replies(26): >>44010808 #>>44010923 #>>44011434 #>>44011854 #>>44011858 #>>44011954 #>>44012172 #>>44012250 #>>44012251 #>>44012503 #>>44012606 #>>44012629 #>>44013306 #>>44013367 #>>44013381 #>>44013473 #>>44013576 #>>44013719 #>>44013871 #>>44013899 #>>44014263 #>>44014585 #>>44014770 #>>44014917 #>>44014928 #>>44018375 #
    CuriouslyC ◴[] No.44010923[source]
    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 level report that's comparable to what a solid human beta reader would provide in seconds.
    replies(3): >>44010944 #>>44011563 #>>44013373 #
    1. wewewedxfgdf ◴[] No.44010944[source]
    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.

    replies(5): >>44011045 #>>44011815 #>>44013284 #>>44013588 #>>44013881 #
    2. thingsilearned ◴[] No.44011045[source]
    companion or replacement?
    replies(3): >>44011187 #>>44012053 #>>44012242 #
    3. Terr_ ◴[] No.44011187[source]
    ... Or saboteur. :p
    4. yujzgzc ◴[] No.44011815[source]
    You're absolutely right! My mistake. I'll be careful about apologizing too much in the future.
    replies(1): >>44012834 #
    5. tonyhart7 ◴[] No.44012053[source]
    they would replace entire software department until AI make bug because endless changes into your javascript framework then they would hire human again to make fix

    we literally creating solution for our own problem

    replies(1): >>44015575 #
    6. surgical_fire ◴[] No.44012242[source]
    They are a replacement if your job is only to write code.

    Especially if your code contains a few bugs, misconceptions, and is sometimes completely unable to fix mistakes, going back and forth into the same wrong solutions.

    This is not to say that AI assistants are useless. They are a good productivity tool, and I can output code much faster, especially for domains I am very familiar with.

    That said, these starry-eyed AI circlejerk threads are incredibly cringe.

    7. DonHopkins ◴[] No.44012834[source]
    You sound like a Canadian LLM!
    replies(1): >>44015299 #
    8. paganel ◴[] No.44013284[source]
    > It is absolutely the greatest golden age in programming ever

    It depends, because you now have to pay in order to be able to compete against other programmers who're also using AI tools, it wasn't like that in what I'd call the true "golden age", basically the '90s - early part of the 2000s, when the internet was already a thing and one could put together something very cool with just a "basic" text editor.

    replies(1): >>44016089 #
    9. conartist6 ◴[] No.44013588[source]
    Wow yeah I'm old enough to remember when the focus wasn't on the programmers, but on the people the programs were written for.

    We used to serve others, but now people are so excited about serving themselves first that there's almost no talk of service to others at all anymore

    10. theropost ◴[] No.44013881[source]
    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! "
    replies(4): >>44014908 #>>44014910 #>>44016378 #>>44018328 #
    11. Workaccount2 ◴[] No.44014908[source]
    I don't know if you have used 2.5, but it is the first model to disagree with directions I have provided...

    "..the user suggests using XYZ to move forward, but that would be rather inefficient, perhaps the user is not totally aware of the characteristics of XYZ. We should suggest moving forward with ABC and explain why it is the better choice..."

    replies(1): >>44015360 #
    12. ◴[] No.44014910[source]
    13. smoyer ◴[] No.44015299{3}[source]
    Eh?
    14. redog ◴[] No.44015360{3}[source]
    It really gave me a lot of push back once when I wanted to use a js library over a python one for a particular project. Like I gave it my demo code in js and it basically said, "meh, cute but use this python one because ...reasons..."
    replies(1): >>44016396 #
    15. roflyear ◴[] No.44015575{3}[source]
    Or, just let their users deal with the bugs b/c churn will be less than the cost of developers.
    replies(1): >>44018617 #
    16. danieldk ◴[] No.44016089[source]
    One could put something cool together without internet using Delphi. The Borland IDEs were ahead of their time - built-in debugger, profiler, and pretty good documentation. My 'internet' was the SWAG Pascal snippet collection (which could be used fully offline). Someone converted it to HTML:

    http://www.retroarchive.org/swag/index.html

    17. rad_gruchalski ◴[] No.44016378[source]
    You must be confusing „intelligence” with „statistically most probable next word”.
    18. rad_gruchalski ◴[] No.44016396{4}[source]
    Wow, you can now pay to have „engineers” being overruled by artificial „intelligence”? People who have no idea are now going to be corrected by an LLM which has no idea by design. Look, even if it gets a lot of things right it’s still trickery.

    I get popcorn and wait for more work coming my way 5 years down the road. Someone will have tidy this mess up and gen-covid will have lost all ability to think on their own by then.

    19. stirfish ◴[] No.44018328[source]
    One trick I found is to tell the llm that an llm wrote the code, whether it did or not. The machine doesn't want to hurt your feelings, but loves to tear apart code it thinks it might've wrote.
    replies(1): >>44018387 #
    20. jghn ◴[] No.44018387{3}[source]
    I like just responding with "are you sure?" continuously. at some point you'll find it gets stuck in a local minima/maxima, and start oscillating. Then I backtrack and look at where it wound up before that. Then I take that solution and go to a fresh session.
    21. scottmf ◴[] No.44018617{4}[source]
    Right. Look at Electron apps. They're ubiquitous despite the poorer performance and user experience because the benefits outweigh the negatives.

    Maintaining a codebase isn't going to be a thing in the future, at least not in the traditional/current sense.