hoqqanen

Appreciate the reply, this is simpler than my thinking and I like it!

Thanks for the note! This part needs work and I really appreciate the call out. I'll try to explain here to share, and maybe clarify my own thinking.

Getting any of the guesses right counts as a win, and you get different guessing slabs for each guess (this latter part isn't made at all clear upfront).

If you have a rule in your head like "no red", but the true rule is "no red or orange", it's possible that on the guessing slabs those two rules evaluate to the same things (e.g. there weren't any oranges present in the guessing slabs). You could then try the rest of the guessing slabs, which might have an example where you get it wrong, giving more gameplay.

I wanted to give a victory on any subset of 5 slabs guessed successfully since trying to get all the guesses is very hard (especially the first guess on many puzzles), and you can get new information from guesses which fail, which offers some progression. Hence getting "you won" and the ability to reveal the rule (I've also thought about keeping the reveal unavailable until you do all guesses) and the invitation to keep playing.

If you have a minute I'd love to hear from you if that makes sense and if you have thoughts about what might make more sense. I've also tried to consider ways of restructuring the gameplay, e.g. automatically progressing to the next set of guessing slabs, such that the flow here is less confusing.

Thanks for playing, and for sharing!

Thanks for the note and the feedback about the instructions! Got me to rework the wording.

The results of the categories look similar to what happens when prompting ChatGPT with "describe a list of {genres/moods/etc.} for <content>". Also the links are all for query pages on amazon/spotify/etc, which says LLM to me (rather than a database). This dynamic schema generation -> UI supported query builder seems like a really interesting direction. I'd love to see it for the web more generally and I bet Exa.ai+LLM of choice would be a pretty good place to start. If it's an LLM I'm curious about hallucination rates and excited for future web-level RAG in only returning real objects.

Also you can supply content which doesn't exist and it will automatically infer genre and such (another strong indication of LLM). I.e. you can imagine the aesthetics of the kind of content you might want by title and then use the UI to explore real recs related to that.

PS to the creator: I love the simplicity of the design and the execution is inspiring. Sent a dollar for my searches :-)

Will also add I've won 7 of 7 so far by using only emojis.