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

AI-enhanced development makes me more ambitious with my projects

simonwillison.net

Post reply on HN
Print view View original

451–460 of 519 posts

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

#451

Post by sokoloff »

famahar wrote: post #449
sokoloff wrote: post #255

Earlier quoted context omitted.

Enlighten me, please. What’s the killer use case where you’ve seen significant leverage from an AI tool? What was the business problem and what were the resulting prompts to your AI junior dev?

I see a lot of skepticism like this on hackernews. People constantly downplaying how impressive this technology is. It's great to be critical. But most of the criticism is too stuck in the present. If it's already as good as many stackoverflow answers, what kind of potential will we see in 1 year, 3 years, a decade. This is massive paradigm shift in the way we program and this conversation thread will be look outdate…

As a skeptic, this reads like "look how great Google search is at finding stackoverflow answers already; imagine how good it will be in a decade!"

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

#452

Post by spookybones »

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 article about, say, an iPad, and it will give you a lot of generic, but well-written content devoid of any tech specs. Add tech specs and use lose the style. What should be a simple fluff piece takes a couple of hours to get the balance right. Or try creating a visual work of, say, two people running down a street, holding hands, and unless you’re very open to interpretation, many hours later, you still won’t have anything approximating what you imagined. You change the “camera” angle, and they’re no longer holding hands. You add a small detail, and the entire scene morphs, etc. I’m saying this as someone who also uses weights and negative prompts. I look forward to further advances, though I’m perfectly happy if these skills remain in the realm of humans.

I will admit chatgpt and copilot are very good at offering up bite-sized pieces of code, like particular objects and functions as well as templates.

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

#453

Post by elorant »

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'm on the same boat. Every time I asked it to provide C# code it gives me back crap. Nine out of 10 times it’s using non-existing libraries. The same thing happened the other day when I asked an SQL Query. I’m still on ChatGPT 3.5 though, perhaps 4 is way better.

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

#454

Post by Forgeties79 »

gibolt wrote: post #447
zikduruqe wrote: post #399

Earlier quoted context omitted.

I should ask ChatGPT if it can take 2 strokes off my game.

Should be achievable, as long as you're not Jerry

OH WE’RE WELL PAST THAT JERRY.

Kills me every time haha

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

#455

Post by spookybones »

esalman wrote: post #220
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…

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.

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

#456

Post by ChrisMarshallNY »

digging wrote: post #431
ChrisMarshallNY wrote: post #339

Earlier quoted context omitted.

These are "Because I can find an exception, your position is invalid." arguments. Not sure I can recall the exact fallacy title, but it's a fairly typical debating tactic.

I disagree that there's a fallacy at play here. The GP (GGP) should support their bold claim that "times have changed" and "people/teams aren't the same as they used to be." If anything, that's an extremely common fallacy and is not to be believed without sufficient evidence.

Actually, that's a fairly typical thing to say to someone that's older, and has lived through those times.

And I am sorry. Things definitely used to be better than they are now, in some ways, and definitely used to be worse, in other ways (for example, it used to be a very white, very male demographic). It's not my fault that things went the way they did. Folks liked money, so folks built a culture that maximized profit, and eschewed humanity.

I am quite sorry about that, but it doesn't change the fact that it was not always so.

It's not in my personal interest to go about creating a slideshow on "how things used to be." I know what I know. I lived it. I ran teams, exactly like I described, and I was a proud member of very large, high-functioning teams that stuck together for decades without stabbing each other in the back.

Let's just agree to disagree, then, eh?

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

#457

Post by w4ffl35 »

famahar wrote: post #449
sokoloff wrote: post #255

Earlier quoted context omitted.

Enlighten me, please. What’s the killer use case where you’ve seen significant leverage from an AI tool? What was the business problem and what were the resulting prompts to your AI junior dev?

I see a lot of skepticism like this on hackernews. People constantly downplaying how impressive this technology is. It's great to be critical. But most of the criticism is too stuck in the present. If it's already as good as many stackoverflow answers, what kind of potential will we see in 1 year, 3 years, a decade. This is massive paradigm shift in the way we program and this conversation thread will be look outdate…

i keep emphasizing this: i don't think we'll be programming any more down the line, i think we'll be engineering with an AI assistant like tony stark. obviously i could be mistaken but it looks like things are heading in that direction.

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

#458

Post by anigbrowl »

ihatepython wrote: post #115
worldsayshi wrote: post #80

Earlier quoted context omitted.

What holds me back the most from using these tools is the vagueness of the copyright situation. I wouldn't straight out want to use it at work. For hobby projects that I might want to use for something serious one day, I'm on the fence. Developers who use this for serious stuff, how goes your reasoning? Is it just a calculated risk? Reward is greater than the risk?

> 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…

[flagged]

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

#459

Post by FleaFlicker99 »

clnq wrote: post #448
ihatepython wrote: post #60

Earlier quoted context omitted.

> How many colleagues could you ask "Can you write me a PoC for a horizontally scalable, probabilistic database in Rust, using Raft-based consensus? I couldn't agree more. I work as a software engineer in the medical field (think MRI's, X-rays, that sort of thing). I've started using ChatGPT all the time to write the code, and then I just fix it up a bit. So far it's working great!

A strong agree as well. This is going to help me a lot in writing software for large passenger aircraft. The integer types GPT gives me aren't the largest, but I think it knows what it's doing.

The great thing is it can repurpose the code from the old inertial guidance unit since the new one is so close it's basically the same thing. I think that GPT thinks it knows what it's doing.

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

#460

Post by still_grokking »

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 a few lines by hand.

All in all it's much easier to come up with some more reasonable solution in a shorter time by just doing it the "classical" way: Read the docs and copy-paste code snippets from proper curated examples some human actually tested.

I don't say that an AI could not program at some point in the future. But I guess it would require AGI to be competitive with people who actually know what they're doing. But at the time we have AGI we have anyway much larger "problems" than how to write code, as more or less all human intellectual work would be superfluous.

Post reply on HN