Skip to main content

On Sale: GamesAssetsToolsTabletopComics
Indie game storeFree gamesFun gamesHorror games
Game developmentAssetsComics
SalesBundles
Jobs
TagsGame Engines
(+1)

With the types of questions and answers, I'm not sure why you needed to use an llm instead of a traditional text parser. I'd imagine that an llm might work better to mark answers correct when they get the gist of it right, but I had the same issue as the other commenter with the inputs being extremely picky about wording/prasing.  (For example it didn't accept 'scary movies' for one puzzle or 'they have to/are forced to' for another, despite those being basically the answer)

If it's going to be that picky, there's no reason not to use a traditional parser.

Hi, thanks for the feedback!

Apparently my API key expired so it marked everything as incorrect... I fixed it now. But I do agree that the AI can be a bit restrictive with the answers that it accepts. I plan on either relaxing it more or making it return text that will guide the user to the correct answer.

If you want, you can try to play the game again and review the AI's actual responses.