AI-enhanced development makes me more ambitious with my projects • Hacker News Board

Re: AI-enhanced development makes me more ambitious with my projects

#461

Post by burnished » Fri, Mar 31, 2023, 5:56 PM UTC

ren_engineer wrote: post #410

ThePhysicist wrote: post #30

What I really love is the unbounded optimism of the AI. How many colleagues could you ask "Can you write me a PoC for a horizontally scalable, probabilistic database in Rust, using Raft-based consensus?" that would then just think for a second and go "Certainly! Let's start by ...". These people exist, but they're one in a thousand (or million?). ChatGPT basically does that for almost every prompt you throw at it. So…

Am I the only one that's been disappointed with GPT for coding? It's good at using common libraries and frameworks but for stuff using more niche libraries it fails miserably almost every time, to the extent that by the time I've debugged and written prompts to try and get it to do it properly I've spent more time than needed still good for handling a lot of grunge work and really useful for doing the stuff where I'm…

Same. I was worried about my job at first - a chatbot being even occasionally factually correct was shocking - but the limitations became much clearer when its proffered solutions relied entirely on hallucinations.

Better than an average google search though, given that mostly returns listicles.

Re: AI-enhanced development makes me more ambitious with my projects

#462

Post by burnished » Fri, Mar 31, 2023, 6:00 PM UTC

withinboredom wrote: post #39

ThePhysicist wrote: post #30

What I really love is the unbounded optimism of the AI. How many colleagues could you ask "Can you write me a PoC for a horizontally scalable, probabilistic database in Rust, using Raft-based consensus?" that would then just think for a second and go "Certainly! Let's start by ...". These people exist, but they're one in a thousand (or million?). ChatGPT basically does that for almost every prompt you throw at it. So…

How do you know it is even close to correct? When I’ve asked it for code, it has been subtly wrong, or worse, correct but missing important edge cases that it doesn’t even seem to be aware of.

Tests. Do you not write tests?

When I've asked for code it has been very wrong, the sweet spot appears to be things that you don't know off hand but can verify easily.

Re: AI-enhanced development makes me more ambitious with my projects

#463

Post by arcatech » Fri, Mar 31, 2023, 6:02 PM UTC

ddren wrote: post #347

ihatepython wrote: post #115

Earlier quoted context omitted.

> Developers who use this for serious stuff, how goes your reasoning? Is it just a calculated risk? Reward is greater than the risk? It seems obvious that AI is the future, and that ChatGPT is the most advanced AI ever created. For me (in the medical industry), if something goes wrong and someone dies a horrible death, I can just say that I didn't write that code, ChatGPT did. Not my fault. Next time you are at the h…

I would trust ChatGPT code about as much as I trust the code produced by any human. All the Therac-25 code was written by a human, so what is the argument here exactly? At least when you tell ChatGPT that its code is wrong it agrees and tries to fix. Ok, it usually fails at fixing it, but it doesn't refuse to acknowledge that there is a problem at all, unlike the case of the Therac-25. I like to think that it is not…

In general we would like developers/engineers to know as much as possible about the things they're engineering. ChatGPT-based development encourages the opposite.

Re: AI-enhanced development makes me more ambitious with my projects

#464

Post by still_grokking » Fri, Mar 31, 2023, 6:05 PM UTC

Elte wrote: post #423

ren_engineer wrote: post #410

Earlier quoted context omitted.

Am I the only one that's been disappointed with GPT for coding? It's good at using common libraries and frameworks but for stuff using more niche libraries it fails miserably almost every time, to the extent that by the time I've debugged and written prompts to try and get it to do it properly I've spent more time than needed still good for handling a lot of grunge work and really useful for doing the stuff where I'm…

I've started to use ChatGPT for semi high-level questions only this week, and I'm with you. It has hallucinated quite a few nonexistent functions, and it's generally unhelpful slightly more often than it is helpful. Just now I asked it why an ` ` and a ` ` with the same CSS had different heights (I've managed to avoid CSS for a while, shoot me XD), and gave it the CSS applied. It suggested the default browser styling…

Googling "why an and a with the same CSS had different heights" and pressing "I'm lucky" would give you the correct answer in seconds.

The AI is just a great waste of time in almost all cases I've tried so far. It's not even good at copy-pasting code…

Re: AI-enhanced development makes me more ambitious with my projects

#465

Post by FleaFlicker99 » Fri, Mar 31, 2023, 6:05 PM UTC

ren_engineer wrote: post #410

ThePhysicist wrote: post #30

What I really love is the unbounded optimism of the AI. How many colleagues could you ask "Can you write me a PoC for a horizontally scalable, probabilistic database in Rust, using Raft-based consensus?" that would then just think for a second and go "Certainly! Let's start by ...". These people exist, but they're one in a thousand (or million?). ChatGPT basically does that for almost every prompt you throw at it. So…

Am I the only one that's been disappointed with GPT for coding? It's good at using common libraries and frameworks but for stuff using more niche libraries it fails miserably almost every time, to the extent that by the time I've debugged and written prompts to try and get it to do it properly I've spent more time than needed still good for handling a lot of grunge work and really useful for doing the stuff where I'm…

I've so far found it almost entirely useless for code (mostly Scala, no big surprise there), but for suggesting tools / alternatives, big picture stuff it's come up with some interesting ideas.

If I was hacking Javascript or Python, especially gluing together common components, I'm sure I'd have a different experience.

Re: AI-enhanced development makes me more ambitious with my projects

#466

Post by esalman » Fri, Mar 31, 2023, 6:06 PM UTC

spookybones wrote: post #455

esalman wrote: post #220

Earlier quoted context omitted.

I was never a graphics/3D designer but ChatGPT basically unlocked a potential new skillet for me.

What have you produced with it? I’m genuinely curious. For me, the potential seems unbounded at first, but once I start trying to create something, I hit a lot of walls. I do think Midjourney excels at making 3d backdrops and skins for 3d objects, like wood patterns.

I just asked ChatGPT to give me an example of a 3d object generation using WebGL, then to make necessary modification in the code to make the object rotate.

Re: AI-enhanced development makes me more ambitious with my projects

#467

Post by still_grokking » Fri, Mar 31, 2023, 6:07 PM UTC

taternuts wrote: post #422

ren_engineer wrote: post #410

Earlier quoted context omitted.

Am I the only one that's been disappointed with GPT for coding? It's good at using common libraries and frameworks but for stuff using more niche libraries it fails miserably almost every time, to the extent that by the time I've debugged and written prompts to try and get it to do it properly I've spent more time than needed still good for handling a lot of grunge work and really useful for doing the stuff where I'm…

> useful for doing the stuff where I'm weaker as a "full stack" developer I'm really excited about this part; I've been using it to help with DevOps stuff and it's been giving me so much more confidence in what I'm doing as well as helping me complete the task much quicker.

Have you double checked everything it told you as you should do with any AI generated output all the time as it's not reliable in any way?

Re: AI-enhanced development makes me more ambitious with my projects

#468

Post by andreyk » Fri, Mar 31, 2023, 6:07 PM UTC

spookybones wrote: post #452

I’ve found that AI prompting has been nearly as time consuming as doing it myself from the get-go. This includes content writing and visual art. Maybe I’m an edge case. I’m not a skilled programmer. However, I’m a decent writer and painter. At most, it generates quick, solid, though generic ideas. Unfortunately, I have to do a lot of reverse engineering and curation to make any valuable changes. Try writing a tech ar…

I've definitely found this to be the case with writing. ChatGPT gets you a "valid" output, but usually a bland and lame one. I think it's better for editing and brainstorming, or for simple tweaks. Specialized tools like SudoWrite are actually more useful as part of a writing work flow.

Pardon the plug, but I co-wrote a little blog post about this with concrete examples, if it is of interest: https://open.substack.com/pub/storiesbyai/p/chatgpt-for-crea...

Re: AI-enhanced development makes me more ambitious with my projects

#469

Post by jliptzin » Fri, Mar 31, 2023, 6:15 PM UTC

still_grokking wrote: post #460

spookybones wrote: post #452

I’ve found that AI prompting has been nearly as time consuming as doing it myself from the get-go. This includes content writing and visual art. Maybe I’m an edge case. I’m not a skilled programmer. However, I’m a decent writer and painter. At most, it generates quick, solid, though generic ideas. Unfortunately, I have to do a lot of reverse engineering and curation to make any valuable changes. Try writing a tech ar…

It's the exact same for code tasks. The AI is actually quite a waste of time… You need to check every word of the AI for truth anyway, so you need to research all the stuff it tells you, as it could be made up, everything it tells you is very shallow, so you need to dig into the topics anyway, and making even small changed by the AI requires ridiculous amounts of explaining details in prose, instead of just changing…

It definitely speeds up my programming but it makes mistakes here and there (like any programmer) that need to be fixed. For me it’s a lot faster to proofread code or adjust the prompt than write it from scratch. And of course there’s cases where the AI can’t come up with a decent solution and it needs to be written from scratch.

Anyone saying programming jobs are in trouble don’t really know programming. You can’t just have someone from the bizdev team prompting ChatGPT for JavaScript code and just doing copy/paste…it would be difficult to even come up with the prompt without sufficient programming jargon knowledge.

Like the article says, the tool will allow programmers to work faster and therefore tackle more things. Expectations will go up but I don’t think the jobs themselves are in trouble.

Re: AI-enhanced development makes me more ambitious with my projects

#470

Post by TaylorAlexander » Fri, Mar 31, 2023, 6:24 PM UTC

spookybones wrote: post #452

I’ve found that AI prompting has been nearly as time consuming as doing it myself from the get-go. This includes content writing and visual art. Maybe I’m an edge case. I’m not a skilled programmer. However, I’m a decent writer and painter. At most, it generates quick, solid, though generic ideas. Unfortunately, I have to do a lot of reverse engineering and curation to make any valuable changes. Try writing a tech ar…

I’ve not actually tried using it for writing help yet, though we’ve had a lot of interesting conversations. My thinking is that when I do some writing, I’ll give it my plan and then ask it for specific content or topic suggestions based on writers and philosophers I’m interested in, or other goals. Then I will write the piece myself, feed it to GPT-4, and ask it for feedback and advice. I’ll re-state my goals and ask it how I’m doing.

I absolutely would not expect it to fully write what I want, but I’ve found it very thoughtful for analysis so far in our conversations.