Live data from Hacker News

AI-enhanced development makes me more ambitious with my projects

simonwillison.net

331–340 of 519 posts

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

#331

The evolution of comments here on HN are telling. 1 month ago people were saying there was no way AI could do their job and many were telling everyone to calm down as nothing would happen. Now one month later this entire thread is about how chatGPT is an integral part of the development process. There are people even saying it replaces junior developers completely. Can anyone venture to guess what the thread will loo…

You also have to think about comments sections not being a random sample of the site’s users.

Likely, a month ago, anyone was interested in commenting on AI threads, so more skepticism was evident. Now, most people who are AI-skeptic are probably tired of AI news and have said their piece in other threads, so don’t bother.

fwiw, I’ve tried to use ChatGPT to make a new, useful Elixir library and it failed miserably. It makes me wonder if the success with JavaScript/Python uses are because the question and answers are extensively in the training data whereas a relatively novel Elixir program is something it can’t do because it’s not truly “reasoning”. It can’t even get basic command line prompts that are straight from the Elixir or Phoenix docs correct, and it cannot solve the error messages that its code produces like others claim experiencing for JavaScript/Python uses.

If my hunch about training contamination is correct, we’re going to quickly run into not being able to create novel software if we replace everyone with GPT algos, unless their core functionality vastly changes from excellent pattern matching to true reasoning.

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

#332
I wonder how many coders have done exactly this in the last couple of weeks? Using the api to cater the chatgpt system to our liking. I’ve done the same and it’s changing the game for me. Saving hours of time jumping through that small part of a project that I knew would be the bottleneck.

I’ve gone from saying that I’ll need an hour to do something to only needing 15 minutes.

However, I’m good enough at what I do that I can find the problems in the code or notice something out of place or that could be done more securely.

I fear many won’t and lots of junk code is going to find its way into our lives. I worry about things like this when it comes to, for example, Wordpress plug-ins, or add ons to other larger tools that we use.

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

#333
post #238

Earlier quoted context omitted.

I've had the unfortunate luck of working with a couple of people with "senior" in their title that once faced with an error message from a open source library, starts their troubleshooting with searching for the error message and if nothing comes up, opens a issue on the issue tracker and then wait. They didn't even consider digging into the source code of the library to figure things out themselves. I haven't worked…

To me, it is only an issue if they sit still after and do not start to work on something else. But I am unashamed to admit that if I don't find the error in github/gitlab issue tracker, and if it seems to take more than 20 minute to investigate, I'll open an issue then move on (if I already know the library, if it's new to me, I'll assume Pebkac for at least two hour and try to rubber duck the issue)

Depending on how much you have on your plate, this is ideal from a time management perspective. Knowing when and how to delegate is a very important skill. Just because you can do something doesn't mean that it's a good use of your time.

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

#334
post #106

Earlier quoted context omitted.

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).

You can put AI in an iteration loop with a compiler and have it bake a functional test suite overnight. It’s a TDD practitioner’s dream.

Oh. Now that is pretty slick

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

#335
post #205

Earlier quoted context omitted.

Heh, is this a Therac 25 joke?

I cannot step in one of those machines without wondering if there is a hardware cutoff.

I went with a mechanic in a chair lift once. He was very nervous, saying he knows the kind of people who maintain these things, and he knows the kinds of things that can go wrong. I feel the same way about automation, whether it be self driving cars or an X-ray machine. I know the kind of people that program them, and the vast number of ways things can go wrong.

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

#337
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…

Strong disagree. Look at the crunchiest of people who are doing very low level work. I wouldn't say they are really making more than anyone else. In a lot of ways they are at a disadvantage because their skills are very niche and very specific. If they find work it can be good. But it can be a frustrating exercise to find that work.

People pay for productivity, making a product of some sort that has value. These AI tools will increase productivity. And they will only get better with time. That translates into the productivity of people who have mastered these tools as more valuable. They just get more done.

Will syntax issues and other problems be an issue with early AI? Sure, but it will get better. The AI will start to catch more issues and move farther up the stack. We still need to know enough to guide it, but the details required will be fewer.

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

#338
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…

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…

What you describe is basically how coders coming up in the last 10 years have been learning -- specific context from StackOverflow or wherever. Contrast this to the hierarchical textbook learning which came before it the intention of which (I think) typically was to impart knowledge which generalises well.

I think what we have now is more productive but results in worse programmers. I.e. you fix the thing in context, but learn little out of context and have to go back to the source of answers when the next thing comes up. The rate at which answers are sought increases, doesn't decrease. Etc.

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

#339
post #256

Earlier quoted context omitted.

Which pretty much sums up today's work culture. I was just talking about this same exact thing, yesterday. That's absolutely heartbreaking. In the old days, we would have a team, that would compete, as a team, against other corporations. Our team would stick together, work together, and, quite often, function as a unit; leveraging each others' strengths, and compensating for each others' weaknesses. Nowadays, we look…

The idea that nobody saw their coworkers as competition for a promotion, or bonus, or face-time with the boss in the past, and that there are no teams that stick together and work together today, is fanciful at best.

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.

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

#340
post #224
post #98

Earlier quoted context omitted.

Make it write a test suite that you can manually verify/expand as necessary, just like code written by humans. I don't understand this 'but how do you know it works' argument. How do you know the code you wrote yourself works? I hope you don't rely on your superior programming skills to just get it right the first time?

You build a correctness proof in your head by thinking through all the details. That what takes most of the time, and the AI doesn’t relieve you from that. Of course one doesn’t always get everything right, but testing alone is no substitute for deductive thinking about the code’s correctness. And it’s also less fun having to do that for someone else’s code.

ChatGPT can help you that process if you ask it to.

I often paste chunks of code into it just to get a detailed line-by-line explanation of exactly what that code is doing. It's really helpful, especially for convoluted code that you're trying to get a good feel for.

Post reply on HN