Hacker Neue

Preferences
foxygen parent
I think I've been using AI wrong. I can't understand testimonies like this. Most times I try to use AI for a task, it is a shitshow, and I have to rewrite everything anyway.
qweiopqweiop
Have you tried Opus 4.5 (or similar recent models)? With Claude code 2, it's actually harder to mess things up IMO
techblueberry
I remember when about a year ago people were asking the same thing about gpt-4.5, the answer is always “yes, I’ve tried them all”
meindnoch
Ok, but have you tried claude-sonnet-GPT-codex-4.5-thinking-fast? That's the game changer. Anyone saying bad things about vibe coding without trying claude-sonnet-GPT-codex-4.5-thinking-fast is like a dinosaur to me, doomed to extinction. Seriously, give claude-sonnet-GPT-codex-4.5-thinking-fast a try, you'll thank me ;)
qweiopqweiop
Fair. Well personally they didn't work well for me (on a huge, complex codebase) until the latest batch. Now they do.
weakfish
Same. Seems to be the never ending theme of AI.
threethirtytwo
Try Claude. And partner with it on building something complex.
dent9
Yes you want Kiro which uses Claude models under the hood
doug_durham
I don’t know about right/wrong. You need to use the tools that make you productive. I personally find that in my work there are dozens of little scripts or helper functions that accelerate my work. However I usually don’t write them because I don’t have the time. AI can generate these little scripts very consistently. That accelerates my work. Perhaps just start simple.
JSDave
Instead of generating, exporting or copy pasting just seems more reliable to me and also takes very little time.

I think what matters most is just what you're working on. It's great for crud or working with public APIs with lots of examples.

For everything else, AI has been a net loss for me.

63stack
> there are dozens of little scripts or helper functions that accelerate my work. However I usually don’t write them because I don’t have the time

People who write things like this can't expect to be taken seriously.

Before AI you didn't have time to write things that saved you time? So you just ended up spending (wasting) more time by going the long way? That was a better choice than just doing the thing that would have saved you time?

CuriouslyC
Do you tell AI the patterns/tools/architecture you want? Telling agents to "build me XYZ, make it gud!" is likely to precede a mess, telling it to build a modular monolith using your library/tool list, your preferred folder structure, other patterns/algorithms you use, etc will end you up with something that might have some minor style issues or not be perfectly canonical, but will be approximately correct within a reasonable margin, or is within 1-2 turns of being so.

You have to let go of the code looking exactly a certain way, but having code _work_ a certain way at a coarse level is doable and fairly easy.

dent9
We are way beyond this. Now you use your plain text prompt to generate a requirements spec that the AI will follow when implementing your project

https://kiro.dev/

CuriouslyC
Kiro is just trying to build a product around exactly what I'm talking about. I'm not a fan, because it's simultaneously too heavyweight and agents don't respect all the details of the specs it creates enough to make the time investment in super-detailed specs worthwhile.

I have a spec driven development tool I've been working on that generates structured specs that can be used to do automatic code generation. This is both faster and more robust.

dent9
That sounds cool, please do share your tools when they're ready :)
mkozlows
Honestly, even this isn't really true anymore. With Opus 4.5 and 5.2 Codex in tools like Cursor, Claude Code, or Codex CLI, "just do the thing" is a viable strategy for a shockingly large category of tasks.
CuriouslyC
Just do the thing can produce functional code, but even with Opus4.5/Codex5.2, there are still plenty of moments where the way it decides to do something is cringe.
mkozlows
Agree. But it's increasingly the case, IME, that for a a lot of tasks, you can start with that. If it does it well, great. If it does something stupid, it's easy enough to ask it to completely rework the stupid thing in a better way, and it can do it quickly. That's still a huge shift compared to the olden days (three months ago) where you needed to really break things down into small chunks for it to get to a success state.
leptons
>You have to let go of the code looking exactly a certain way, but having code _work_ a certain way at a coarse level is doable and fairly easy.

So all that bullshit about "code smells" was nonsense.

CuriouslyC
A lot of code smells matter more for humans than LLMs (and LLMs have their own unique code smells). For example, nested ternary operators are a great source of bugs in human code, but agents could care less, but humans handle multiple files with the same variable names and lots of duplicated code well, whereas this stuff confuses agents.
leptons
>but agents could care less,

The phrase is "couldn't care less". If you "could care less" then you actually care about it. If you "couldn't care less" then there's no caring at all.

mrwrong
have you tried using $NEWEST_MODEL ?
threethirtytwo
It’s because depending on the person the newest model crossed the line into being useful for them personally. It’s not like a new version crosses the line for everyone. It happens gradually. Each version more and more people come into the fold.

For me Claude code changed the game.

mrwrong
yes, it is trivially true that each new person who recommends LLMs is a new person coming into the fold
threethirtytwo
You get new people recommending the latest version all the time to people who are unconvinced because that version is usually what brought them into the fold.

What you’re mocking is somewhat of a signal of actual improvement of the models and that improvement as a result becoming useful to more and more people.

bdangubic
how much time/effort have you put in to educate yourself about how they work, what they excel at, what they suck at, what is your responsibility when you use them…? this effort is directly proportional to how well they will serve you

This item has no comments currently.

Keyboard Shortcuts

Story Lists

j
Next story
k
Previous story
Shift+j
Last story
Shift+k
First story
o Enter
Go to story URL
c
Go to comments
u
Go to author

Navigation

Shift+t
Go to top stories
Shift+n
Go to new stories
Shift+b
Go to best stories
Shift+a
Go to Ask HN
Shift+s
Go to Show HN

Miscellaneous

?
Show this modal