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

Show HN: I AI-coded a tower defense game and documented the whole process

github.com

Post reply on HN
Print view View original

91–100 of 163 posts

Re: Show HN: I AI-coded a tower defense game and documented the whole process

#91

Post by M4v3R »

mberning wrote: post #88
M4v3R wrote: post #85

Earlier quoted context omitted.

Hard to tell what exactly went wrong in your case, but if I were to guess - were you trying to do all of this in a single LLM/agent conversation? If you'll look at my prompt history for the game from OP you'll see it was created with a dozens of separate conversations. This is crucial for non-trivial projects, otherwise the agent will run out of context and start to hallucinate.

Agent mode in RubyMine which I think is using a recent version of sonnet. I tried starting a new agent conversation but it was still off quite a bit. For me my interest in finessing the LLM runs out pretty quickly, especially if I see it moving further and further from the mark. I guess I can see why some people prefer to interact with the LLM more than the code, but I’m the opposite. My goal is to build something. I…

> If I can do in 2 hours of prompting or 2 hours of doing it manually I’d rather just do it manually.

100% agree, if that was the case I would not use LLMs either. Point is, at least for my use case and using my workflow it's more like 2 hours vs 10 minutes which suddenly changes the whole equation for me.

Re: Show HN: I AI-coded a tower defense game and documented the whole process

#92

Post by mordechai9000 »

Brajeshwar wrote: post #24

Yours is beautiful; the code is too. I'm sure you had a lot more hand than just using AI. I stopped coding a long time ago. Recently, after a few friends insisted on trying out AI-Assistance codes and I tinkered. And all I came up was a Bubble Wrap popper, and a silencer. :-) https://bubble-pop.oinam.com https://void.oinam.com

Running chrome on android and the bubbles aren't popping for me. Count is staying at zero. Are you open to PRs? :-)

Re: Show HN: I AI-coded a tower defense game and documented the whole process

#93

Post by tills13 »

nichochar wrote: post #81
tills13 wrote: post #80

[flagged]

Isn't creativity always impressive if done well? Code is a medium, painting is a medium, piano is a medium, and prompting is a medium. This sounds a little bitter.

Prompting is telling someone or something else to do something for you. Is management creative?

The most creative aspect of this is the idea. The rest is boring.

Re: Show HN: I AI-coded a tower defense game and documented the whole process

#94

Post by AndrewKemendo »

johnrob wrote: post #76
AndrewKemendo wrote: post #68

Earlier quoted context omitted.

> A lot of posts about "vibe coding success stories" Where are you reading “a lot of posts” making this specific claim? I’ve never seen any serious person make such a claim > a strong and thorough idea of what you want, broken up into hundreds of smaller problems, with specific architectural steers on the really critical pieces. This is how I’ve been using LLM bots since CGPT preview and it’s been phenomenally useful…

I see 100x used quite a bit related to LLM productivity. It seems extreme because it implies one could generate a year’s worth of value in a few days. I would think delivering features involves too much non coding work for this to be possible.

But that’s precisely what I’m saying is that what I can do today by myself in a couple of days would have taken me a year with a team of three people

The key limiting factor to any project as somebody else in this thread said was “people alignment are the number one hindrance in project speed”

So 10 years ago if I wanted to make a web application that does complex shit I’d have to go and hire a handful of experts have them coordinate, manage the coordination of it, deliver it, monitor it everything else all the way through ideation storyboarding and everything else

I can do 100% of that myself now, now it’s true I could’ve done 100% of myself previously, but again it took a year of side effort to do it

Re: Show HN: I AI-coded a tower defense game and documented the whole process

#95

Post by mumbisChungo »

qsort wrote: post #12
mgdev wrote: post #6

This is awesome. I've been in software for 20+ years now as well. One thing I've noticed is many (most?) people in our cohort are very skeptical of AI coding (or simply aren't paying attention). I recently developed a large-ish app (~34k SLOC) primarily using AI. My impression is the leverage you get out of it is exponentially proportional to the quality of your instructions, the structure of your interactions, and t…

I commented on this before, I'm in this weird "opinion arbitrage" spot where I'm relatively skeptical by HN standards but I'm actually pushing for more usage at work. Hell, I'm typing this while I wait for Claude to be done. The reason for my skepticism is the delta between what they're being sold as and what they actually do. All AI solutions, including agents (especially agents!), are effectively worse-than-worthle…

It's the same problem that crypto experiences. Almost everyone is propagating lies about the technology, even if a majority of those doing so don't understand enough to realize they're lies.

I'd argue there's more intentional lying in crypto and less value to be gained, but in both cases people who might derive real benefit from the hard truth of the matter are turning away before they enter the door due to dishonesty/misrepresentation.

Re: Show HN: I AI-coded a tower defense game and documented the whole process

#97

Post by iaw »

jslakro wrote: post #52

I didn't find any mention to the costs spent on Claude

I'm using Claude for my side projects. The pricing tiers are Free (for Sonnet 3.5), $20/m for Opus 4, $100/m for max (5x usage limit as $20) and then a $200 tier above that at another 5x I believe.

The usage limits reset every 6 hours.

Re: Show HN: I AI-coded a tower defense game and documented the whole process

#99

Post by sarchertech »

AndrewKemendo wrote: post #94
johnrob wrote: post #76

Earlier quoted context omitted.

I see 100x used quite a bit related to LLM productivity. It seems extreme because it implies one could generate a year’s worth of value in a few days. I would think delivering features involves too much non coding work for this to be possible.

But that’s precisely what I’m saying is that what I can do today by myself in a couple of days would have taken me a year with a team of three people The key limiting factor to any project as somebody else in this thread said was “people alignment are the number one hindrance in project speed” So 10 years ago if I wanted to make a web application that does complex shit I’d have to go and hire a handful of experts hav…

If 100x was really possible, it would be instantly, undeniably obvious to everyone. There would be no need for people alignment because one lone developer could crank out basically anything less complicated than an OS in a month.
Post reply on HN