Skip to main content

Indie game storeFree gamesFun gamesHorror games
Game developmentAssetsComics
SalesBundles
Jobs
TagsGame Engines

MJ already said a lot of what I was going to say, lol, so I’m not going to repeat it, but simply state that I agree with their critique. However, I think I can shed some light on why engagement suffered so much.

I see on your game page that you used AI, which was my suspicion as I read the text of the nodes. AI (particularly GPT) as a flair for trying to be poetical (“Your boots remember the stones”, or something like that from one of the transits -> hallmark AI.). I myself use AI heavily during dev, so this is not a knock on you; When asking AI to create text content, I honestly wonder whether the juice is worth the squeeze sometimes, because I end up having to rewrite so much to make it more engaging. My guess is that you relied a lot upon AI to assist you in constructing some of your vision, and it 1) may have gone a little off the rails in this regard and 2) been the source of your bugs.

With working with AI in game dev, one of the things I am learning to do is bite sized approaches, and laying out as much of the game ahead of time as possible so that the AI doesn’t mess it up. The AI can be a great helper, but it’s also going to steer you wrong if you let it (i.e. AI slop). I have in my head to make a tutorial on AI use in game dev one of these days to talk about the strengths and limitations of it, and best practices in using it.

I think the game concept is very strong, and you showed some real polish - a great menu system, sound controls, etc - This is one thing that I see lacking often, and I am glad to see it here. Same with music and systems. Game narrative and writing, however, need to be examined more closely. Please let me know if this was helpful, I am looking forward to your next entry!

(+1)

Thanks for the feedback! And indeed, I do agree!

Practically for this jam I ran out of time, my original vision was to not use gen AI for dialogue or story content, but when I was looking down at the barrel at 3h left in submission and most still being unwritten, I just put it through gen AI machine to fill my fluent keys. It was a choice between not publishing, publishing something much less or using non-curated AI to write me stuff (I had written a story bible so it helped a bit). I chose the latter, but there were no good choices. I overscoped and failed in that :D

Actually, I managed to make the critical bug fixes a few minutes past the jam game, and I continued the project immediately on here:

https://lazyanttu.itch.io/the-unstable-key

That now has about 60-70% of the content written by me (I have replaced the majority of the AI-written stuff), with lots of bug fixes, and is much better. Of course, the rating is based on what I submitted on the jam, but I wanted to share some post-jam progress! :)


That was helpful to confirm my suspicion that it was a good idea to continue replacing the prose. I also think the issue is that there is so much variance in quality; I wrote some segments of the game carefully, and then there is a lot of slop. So those kinds of conflict with each other.

So the plan to use gen AI to write was not plan A; it was plan B once I ran out of time.

(1 edit) (+1)

Yeah, totally get that. I had (and have) the same situation with games I created for school - I realized how important it is to have a writer that is dedicated to this task for a game that is narratively heavy. No shade, glad we’re on the same page, lol