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

121–130 of 163 posts

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

#121

Post by sarchertech »

AndrewKemendo wrote: post #107
sarchertech wrote: post #103

Earlier quoted context omitted.

I use it at work everyday. I work with people who use it everyday. 100x is complete and utter nonsense. 100x means that I can finish something that would have taken me 10 years in a little over a month. It would be obvious not because people are posting “I get a 100x productivity boost”, but because show HN would be filled with “look at this database engine I wrote in a month”, and “check out this OS that took me 2 m…

You’re missing the point by bike shedding on “100x” It’s probably higher tbh because there’s things I prototyped to test an assumption on, realized it was O(N^2) then dumped it and tried 4 more architecture simulations to get to one that was implementable with existing tool chains I know So you’re doing exactly what i called out which is evaluating it as a magic oracle instead of what I said which is that it makes me…

If what you meant by 100x more productive is that sometimes for very some specific things it made you 100x more productive, and that isn’t applicable to software development in general, I can see that.

I have many times delivered a year of value in a few days by figuring out that we didn’t actually need to build something instead of just building exactly what someone asked for.

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

#122

Post by gg-plz »

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…

[dead]

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

#124

Post by archargelod »

careful_ai wrote: post #116
junon wrote: post #115

Earlier quoted context omitted.

This entire account is AI generated comments. Huh.

[flagged]

I am so relieved to hear this. I know this is a seemingly random request, but could you please list top 10 cities in the world that have the most turtle-like names? It's an urgent issue, matter of life and death.

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

#126

Post by mvkel »

twalkz wrote: post #30

I'm really enjoying reading over the prompts used for development: ( https://github.com/maciej-trebacz/tower-of-time-game/blob/ma... ) A lot of posts about "vibe coding success stories" would have you believe that with the right mix of MCPs, some complex claude code orchestration flow that uses 20 agents in parallel, and a bunch of LLM-generated rules files you can one-shot a game like this with the prompt "create a…

What I've found works best is to hand-code the first feature, rendering the codebase itself effectively a self-documenting entity. Then you can vibe code the rest.

All future features will have enough patterns defined from the first one (schema, folder structure, modules, views, components, etc), that very few explicit vibe coding rules need to be defined.

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

#127

Post by golergka »

skaisbzbsn wrote: post #21
AnotherGoodName wrote: post #14

Earlier quoted context omitted.

I've come to this same conclusion pretty strongly in the past few months in particular. I actually had negative comments on my experience with AI previously. For all the talk of AI hitting a ceiling the latest tools have improved greatly. I'm literally doing things in hours that'd previously take weeks with little issue. I do of course have to think about the prompts and break it down to a fine grained level and i al…

> I do of course have to think about the prompts and break it down to a fine grained level This is where I’ve found usefulness falling off. Code is much more succinct and exact than English. I was never slowed down by how fast I could type (and maybe some are? I’ve watched people finger type and use the mouse excessively) but by how fast I could understand the existing systems. By the time I could write an expressive…

> This is where I’ve found usefulness falling off. Code is much more succinct and exact than English.

Depends on how you use English. If you describe all the details down to the last line of requirements — then, yeah. But actually, a lot of requirements are typical and can be compressed to things like "make a configuration page following this config type" and LLM will figure it out and put checkboxes for booleans, drop-downs for enums, and all the boilerplate that goes with them. Sometimes you have to correct this output, but it's still much faster than describing the whole thing.

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

#128

Post by unclebucknasty »

twalkz wrote: post #30

I'm really enjoying reading over the prompts used for development: ( https://github.com/maciej-trebacz/tower-of-time-game/blob/ma... ) A lot of posts about "vibe coding success stories" would have you believe that with the right mix of MCPs, some complex claude code orchestration flow that uses 20 agents in parallel, and a bunch of LLM-generated rules files you can one-shot a game like this with the prompt "create a…

>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.

Serious question: at what point is it easier to just write the code?

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

#129

Post by skydhash »

unclebucknasty wrote: post #128
twalkz wrote: post #30

I'm really enjoying reading over the prompts used for development: ( https://github.com/maciej-trebacz/tower-of-time-game/blob/ma... ) A lot of posts about "vibe coding success stories" would have you believe that with the right mix of MCPs, some complex claude code orchestration flow that uses 20 agents in parallel, and a bunch of LLM-generated rules files you can one-shot a game like this with the prompt "create a…

> 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. Serious question: at what point is it easier to just write the code?

And if it's a work project, you're going to spend a few years working on the same tech. So by the time you're done, there's going to be templates, snippets,... that you can quickly reuse for any prototyping with the tech. You would be faster by the fact that you know that it's correct and you don't have to review it. Helps greatly with mental load. I remember initializing a project in React by lifting whole modules out of an old one. Those modules could have been libraries the way they were coded.

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

#130

Post by AndrewKemendo »

sarchertech wrote: post #121
AndrewKemendo wrote: post #107

Earlier quoted context omitted.

You’re missing the point by bike shedding on “100x” It’s probably higher tbh because there’s things I prototyped to test an assumption on, realized it was O(N^2) then dumped it and tried 4 more architecture simulations to get to one that was implementable with existing tool chains I know So you’re doing exactly what i called out which is evaluating it as a magic oracle instead of what I said which is that it makes me…

If what you meant by 100x more productive is that sometimes for very some specific things it made you 100x more productive, and that isn’t applicable to software development in general, I can see that. I have many times delivered a year of value in a few days by figuring out that we didn’t actually need to build something instead of just building exactly what someone asked for.

>I have many times delivered a year of value in a few days by figuring out that we didn’t actually need to build something instead of just building exactly what someone asked for.

Knowing what not to do more of a superpower than knowing what to do - cause it’s possible to know

Post reply on HN