[yamalight]

Built vaporlens.app in my free time using LLMs (specifically gemini, first 2.0-flash, recently moved to 2.5-flash).

It processes Steam game reviews and provides one page summary of what people thing about the game. Have been gradually improving it and adding some features from community feedback. Has been good fun.

[polishdude20]

I usually find that if a game is rated overwhelmingly positive, I'm gonna like it. The moment it's just mostly positive, it doesn't stay as a favorite for me.

[yamalight]

Those games are usually brilliant - but those are very rare. Like "once in a few years" kind of rare IMO. While that is a valid approach, I play way more than that haha!

What I found interesting with Vaporlens is that it surfaces things that people think about the game - and if you find games where you like all the positives and don't mind largest negatives (because those are very often very subjective) - you're in a for a pretty good time.

It's also quite amusing to me that using fairly basic vector similarity on points text resulted in a pretty decent "similar games" section :D

[on_the_train]

That rating is not (just) a function of positive to negative ratio. Small number of reviews (ie small games) can't reach that rating although they might be equally well received.

[muzani]

There's plenty I don't like, like Factorio. It's not bad enough to downvote, but not likeable enough to play.

However, review positivity is usually the best indicator of sales - it's so accurate that there's algorithms that rely entirely on it.