Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ask HN: How is AI-assisted coding going for you professionally?

news.ycombinator.com

Post reply on HN
Print view View original

601–610 of 657 posts

Re: Ask HN: How is AI-assisted coding going for you professionally?

#601

Post by floydian10 »

BoneShard wrote: post #372
viccis wrote: post #268

Haven't seen this mentioned yet, but the worst part for me is that a lot of management LOVES to use Claude to generate 50 page design documents, PRDs, etc., and send them to us to "please review as soon as you can". Nobody reads it, not even the people making it. I'm watching some employees just generate endless slide decks of nonsense and then waffle when asked any specific questions. If any of that is read, it is b…

I noticied what previously would take 30 mins, now takes a week. For example we had a performance issue with a DB, previously I'd just create a GSI (global secondary index), now there is a 37 page document with explanation, mitigation, planning, steps, reviews, risks, deployment plan, obstacles and a bunch of comments, but sure it looks cool and very professional.

Not to mention that now you need an "alignment meeting" with a bunch of people

Re: Ask HN: How is AI-assisted coding going for you professionally?

#602

Post by sjducb »

parliament32 wrote: post #575
sjducb wrote: post #514

Earlier quoted context omitted.

Hi thanks for this brilliant feature. It will really improve the product. However it needs a little bit more work before we can merge it into our main product. 1) The new feature does not follow the existing API guidelines found here: see examples an and b. 2) The new feature does not use our existing input validation and security checking code, see example. Once the following points have been addressed we will be ha…

..so they copy/paste your message into Claude and send you back a +2000, -1500 version 3 minutes later. And now you get to go hunting for issues again.

If that happens then there’s an issue.

In the past I’ve hopped on a call with them and where I’ve asked them to show me it running. When it falls over I say here are the things the system should do, send me a video of the new system doing all of them.

The embarrassment usually shames them into actually checking that the code works.

If it doesn’t then you might have to go to the senior stakeholder and quietly demonstrate that they said it works, but it does not actually work.

You don’t want to get into a situation where “integrate” means write the feature while others get credit.

Re: Ask HN: How is AI-assisted coding going for you professionally?

#605

Post by threethirtytwo »

3form wrote: post #533
threethirtytwo wrote: post #416

Earlier quoted context omitted.

No it doesn't check out. I think it's becoming abundantly clear LLMs learn in real time as they speak to you. There's a lot of denial and people claiming they don't learn that their knowledge is fixed on the training data and this is not even remotely true at all. LLMs learn dynamically through their context window and this learning is at a rate much faster than humans and often with capabilities greater than humans…

You're observing this "paradox", because what you call learning here is not learning in the ML sense; it's deriving better conclusions from more data. It's true for many ML methods, but it doesn't mean any actual learning happens.

There's another phenomenon. It's called pedantic denialism. Deriving conclusions from more data is the same thing as learning. You learned something from the new data hence the new conclusion. As long as that context window survives the LLM has learned.

Re: Ask HN: How is AI-assisted coding going for you professionally?

#607

Post by zaphar »

ytoawwhra92 wrote: post #595
zaphar wrote: post #527

Earlier quoted context omitted.

I am absolutely certain the world isn't just. I'm also absolutely certain the world can't get just unless you let people suffer consequences for their decisions. It's the only way people can world.

IME that simply doesn't work in professional environments. People will either misrepresent the failure as a success or find someone else to pin the blame on. Others won't bother taking the time to understand what actually happened because they're too busy and often simply don't care. And if it's nominally your responsibility to keep something up, running, and stable then you're a very likely scapegoat if it fails. Wh…

I understand how people can get into these fatalist outlooks from experience. I just refuse to lock myself into them. And because I've refused to do so, every once in a while I have success and make the work environment just that little bit better. So I'll keep doing it.

Re: Ask HN: How is AI-assisted coding going for you professionally?

#608

Post by jwr »

jwr wrote: post #171

Measured 12x increase in issues fixed/implemented. Solo founder business, so these are real numbers (over 2 months), not corporate fakery. And no, I am not interested in convincing you, I hope all my competitors believe that AI is junk :-)

It is somewhat amusing that, looking back, my most informative and factually correct comments get downvoted. What gets the most upvotes is agreeing with popular opinion.

Re: Ask HN: How is AI-assisted coding going for you professionally?

#609

Post by dormento »

My experience is that success with AI seems to be directly influenced by what technologies were employed. IA cannot learn further than its own context window when dealing with technologies it has not seen before (like an internally-developed framework). It does a good job on React, but it does a very poor job on a hand-rolled ORM.

For small greenfield stuff and throwaway code though, its generally very useful. For bigger projects, seems to be i tend to have more success with it mocking stuff, populating structures with test data and combing through logs to identify bottlenecks and opportunities for improvement when i've exhausted my tricks.

Post reply on HN