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

101–110 of 519 posts

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

#101

Post by baq »

Thorentis wrote: post #93
baq wrote: post #84

Earlier quoted context omitted.

> Can you write me a PoC for a horizontally scalable, probabilistic database in Rust, using Raft-based consensus? just pasted this into bing creative mode. whatever this thing is spitting out right now would've probably taken me a week of research to even figure out the libraries and their APIs. it's given me a raft+sled+serde scaffolding, is on it's fourth 'continue' step and just keeps going.

How do you know what it created actually works and hasn't just been hallucinated? Have you checked every API call? Is it using non deprecated versions? Does it even run?

i'm pretty sure it won't work, it actually started to lose coherence at the 4th step, but that isn't the point - the point is, i'm already a week ahead in my research since the libraries actually exist! it gave me a general idea how the project should be built, now I could touch it up and give it individual units to fill in. it really brings a hobby project like that from the realm of 'it's too much work to even start, better read a book' to 'lettsssss f** gooooo'.

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

#102

Post by King-Aaron »

shostack wrote: post #12
zamfi wrote: post #6

@Simon, I love this. And one day, in the not too distant future, a few old wizened graybeards, like you and I and the other folks on this site who have been writing code from scratch for 20 years, will be the magicians who walk the earth among mere mortals who only learned to code with the assistance of ChatGPT. We will be the ones with the preattentive syntax parsing in our brains that let us simply see basic syntax…

And then we'll have people praying to the Omnissiah with their prompts.

From the moment I understood the weakness of my flesh, it disgusted me.

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

#103

Post by ZaoLahma »

ummonk wrote: post #27
zamfi wrote: post #6

@Simon, I love this. And one day, in the not too distant future, a few old wizened graybeards, like you and I and the other folks on this site who have been writing code from scratch for 20 years, will be the magicians who walk the earth among mere mortals who only learned to code with the assistance of ChatGPT. We will be the ones with the preattentive syntax parsing in our brains that let us simply see basic syntax…

Our experience coding from scratch will have about as much validity as the experience of people who coded in assembly has today. It'll be a specialized skill with its own niche but without much value in the broader tech industry.

Perhaps the old fashioned programming skills will be applied to writing test cases for the AI generated code.

There are still areas in software development where (not systemized) failure is not an option and where AI generated code absolutely can be useful, but would need careful validation from a human. Not only for unintentional errors, but also for potentially maliciously seeded errors in the model that is being used.

Perhaps manually writing test cases for the AI generated code could meet the requirements for human validation.

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

#104

Post by braindead_in »

zamfi wrote: post #6

@Simon, I love this. And one day, in the not too distant future, a few old wizened graybeards, like you and I and the other folks on this site who have been writing code from scratch for 20 years, will be the magicians who walk the earth among mere mortals who only learned to code with the assistance of ChatGPT. We will be the ones with the preattentive syntax parsing in our brains that let us simply see basic syntax…

Not to forget the time spent agonizing over naming variables.

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

#105

Post by opportune »

anonyfox wrote: post #57

Am I the only one that isn’t blocked by coding speed (I can MVP very fast with lot of techstacks) but with … deployment? Don’t get me wrong, I am a senior DevOps, know my terraform/CDK/… and AWS/heroku/digitalocean/hetzner/vercel/… stuff by heart, so it’s not missing knowledge. But I really hate the maintenance work down the road. I just don’t want to get emails about some deprecated stuff from some provider and have…

Me too. I can code and test pretty fast, but because of the policies where I work, it takes a long time to actually ship a change, and often we only catch bugs then. I’m not talking “time to create and deploy a binary to a cloud region through an API” I’m talking “we have to roll the binary out piecemeal at a slow rate, on purpose” over a little under a week.

So basically, a bug can set you back a long time (multiple weeks). And to reduce the risks of bugs we usually need to ship incrementally. And because bugs are such a hassle we have to monitor and test the crap out of everything, which of course we should be doing anyway, but we do it more than we probably would otherwise. But of course bugs do still happen, and even someone else’s might set you back. A flip side to slow releases is releases tend to batch more changes. And of course that makes finding a bug more time consuming.

So a feature that could take me a few hours to write and test at my top performance basically needs to be budgeted at a month of work. Of course, we have other responsibilities like testing, monitoring, analysis, support, design, coordination, helping others. But dragging out completing a project drags all that out too. If I could ship to staging same day and prod 1-2 days later, I wouldn’t need to plan so much or spend so much time going back and forth about design. We could just meet up about the change and do it that week.

And you might think you could simply parallelize/pipeline more tasks, but overdoing that sets you down the path of overextending yourself. If something important goes off track you need to do everything to get it back on track - if you don’t, it’s going to be really late - and overcommitting eliminates the slack that makes it possible.

Truly, this is something I think about all the time and probably the least favorite aspect of my job. Anyway, unless chatgpt can help me write a persuasive argument that convinced my company to completely 180 its engineering policies, it won’t make me much more productive.

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

#106

Post by simonw »

Thorentis wrote: post #94
ThePhysicist wrote: post #44

Earlier quoted context omitted.

I can read the code and verify it. Sometimes there are small mistakes but overall the architecture and approach are mostly correct. It won't produce 100 % production-grade code, but that's not expected for a PoC. And personally I also get stuff subtly wrong at times, I just iterate and test to find these cases and fix them. So I guess we're not fully replacable yet.

You can't read API calls and know if they're real, or if the function names are plausible but non existent. This is the problem with GPT. It creates great sounding possible APIs, but has no idea which APIs actually exist.

That's the great thing about using GPT for code - unlike factual knowledge, it's very easy to confirm if the code it wrote had errors or not: you run it.

The you test it manually with a few more inputs, then you write some automated tests for it (maybe with GPT's assistance).

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

#107

Post by roel_v »

skybrian wrote: post #63
jfvinueza wrote: post #46

Yes, agree. I mean GPT-4 is an all in all a fantastic tool, but it's especially good for developing. The moment you transform a blurry idea into structured data in any form (and it helps a lot with that: you can chat like two decent citizens and ask it to transform it to json at any given time), you can pretty much generate infinite boilerplate that's consistent through a whole application: interfaces > tables > migr…

I tried using ChatGPT a bit with the GPT4 model and it seems quite promising, but also very slow. When it's writing out the same function again with a change I asked for, it reminds me of the old days when connecting to a BBS with a 300 baud modem. Am I doing it wrong somehow?

No, that's how it is. My MO is now I type in the question to the chat; go to another tab to google a bit on the background of the problem; by the time ChatGPT is done, I already know enough to have a reasonable idea about whether what it came up with is in the general direction of where I want to go. And if it is, I'm usually confident enough that it gets the details then mostly right.

One meta comment is that I would love for something like a Greasemonkey script that can automatically add some checkboxes or something that will then automatically add stock phrases to ChatGPT questions, like 'show me only the code', as I find that a lot of the intro fluff and the explanation of things are useless to me and just take up time. In general, the UI is pretty bare bones, there's a world to be gained there.

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

#108

Post by roel_v »

an_aparallel wrote: post #59
blueorange8 wrote: post #31

Earlier quoted context omitted.

This isn't an example of a coding problem, but just yesterday we had a very difficult technical problem come up that one of our partners, a very large IT company couldn't solve. None of our engineers knew how to solve it after trying for a few days. I would say I'm an expert in the industry and have been doing this over 20 years as a developer. I thought I knew the best way to solve it, but I wasn't sure exactly. I a…

this is exactly the kind of post that folks who say "oh - it wont take our jobs - our jobs are safe (way too advanced for silly AI)" - need to be reading. You're an expert, and it answered an expert question, and your colleagues couldnt do it either...after a few days...and this is just early days.

I don't think this is the take away. I'm in a similar situation as the GP, but the crux is that we still need people to make the decisions on what needs to happen - the computer 'just' helps with the 'how'. You need to be a domain expert to be able to ask the right questions and pick out the useful parts from the results.

I'm also not so worried about 'oh but the machines will keep getting better'. I mean, they will, but the above will still remain true, at least until we get to the point where the machines start to make and drive decisions on their own. Which we'll get to, but by that point, I/we will have bigger problems than computers being better at programming than I am.

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

#110

Post by marginalia_nu »

precompute wrote: post #85
JimmyRuska wrote: post #38

Earlier quoted context omitted.

Having spent a lot of time with GPT-4 recently, it's possible the new generation will not have the same issues we did. For example they can write some code and say, "adjust for best practice". Then "explain why needs to be " Oh this is called , give me an example of it. Give me another example. Give me another example. Give me use cases where this would be better. Give me a short story where it was done my way but it…

Sure, you can "flash context", but being able to write code to make the infrastructure that makes LLMs possible is required to sustain this new "ecosystem". I don't think every dev will be equally hit by this new paradigm, it's basically a two-tier system now, the LLM babysitters and the actual competent human coders (whose input probably gets fed into a LLM).

s/LLM/StackOverflow/g and squint, and you're basically describing the preceding decade.
Post reply on HN