[ddawson]

I do not know how to code, nothing beyond the simplest things but I am obsessed with AI development. Several month’s ago I decided to see if Claude could do the work for me.

My test was to create a tower defense game that would run in a web browser. It took me about eight prompts, each time refining it, including agreeing to the suggesting that Claude recommended and seeing Claude agree with me on the bugs that I pointed out.

It was mind blowing. It’s not pretty at all but is recognizable as a TD game. I thanked Claude and said that was enough and Claude signed off as well saying, well if you’re going to continue to refine it, do these four things. I was really stunned.

[101008]

Honesty question, and leaving aside implications about what's possible and all of that, what was particular positive about the experience?

You didn't do anything, just asked a different entity to do it for you. And nothing noble or original, just a copy of existing games. I see no difference between this and getting a $500 coupon to use at Fiverrr and ask a freelance engineer to do the same while you chat with them.

[atonse]

Is there anything inherently noble about programming if not to solve a real world problem?

If they were doing it for an exam where their skills were being evaluated, that’s one thing. But if they were doing it as a means to an end, does it matter if they found a more efficient way to do it?

[ddawson]

I'm not asking for an award. lol. I'm not sure exactly what you're after here, with asking what was particularly positive.

It's a personal attempt to see how much I can do with an automaton. I could pay someone to do my taxes or file them myself (I'm in the US). There is much more room for frustration but also lots of benefits to the latter.

In particular, with Claude Artifacts, I had a chance to see an amazing innovation. Have you ever wanted to see something new just because it's new? It changes you, which of course is one of the purposes of exploring novelties. By the way, this was my experience in July 2024.

[kypro]

I was talking to some colleagues about this recently, and I think the reason non-coders and amateur coders seem to be so much more impressed by the current state of AI code gen is that they don't fully understand what actually goes into the average software project.

Setting up a simple game on your local machine really isn't that hard. For example, you can probably take an open-source project and with some minor alterations have something working pretty quickly.

But most software development doesn't work like this. You are typically given very explicit requirements and when you're working for a corporate with real customers you have high quality standards that need to be met. Often this is going to require a lot of bespoke code and high-level solutionising which you're not going to get out of some open source project (at least not without significant changes).

Similarly, productionising products requires a lot of work and consideration which spinning something up locally doesn't. You need to think about security, data persistence, hosting, deployment, development environments, documentation, etc, etc, etc...

I think this partly explains why people have such widely different opinions on these tools at the moment. I acknowledge they write pretty good code, but for me they're almost useless in 90% of the things I do and think about as a software engineer.

[fergie]

I suspect, that just like real developers, that Claude is best at "greenfield" projects, but not so good at making changes to existing code generated by other developers or AIs.