Not AI but Ive seen a lot of social startup apps in my time all trying to be the next facebook with a twist. They all end up in the same place. If you have any idea along the lines of "Do/share X with your friends" it has probably been tried a million times before so just don't. Another one is dating apps. Everyone thinks they all suck and everyone thinks they have the new twist that will make it not suck. End result is so many shitty 'ghost town' dating apps that end up looking and functioning like the other 99%. Once in a while a Snapchat or Tindr will break out with a genuinely fresh idea but for every one of those there are a million carcasses of failed startup ideas

Not sure about AI specific but: Todo apps, habit trackers, lots of social media, job boards, recommendation apps, fun things to do with friends, travel planners, trackers (movies/books). I think it’s more common for B2C because these are things that a lot of people come across.

Some of these ideas could maybe be done better now that we have genAI but the question might would it work as a standalone app or is it just a feature?

It's far too soon to call any AI-specific ideas tarpits. Nothing newly made possible by LLMs or generative image models has been tried long enough to give up on. There are no startup bones to dig up yet.

If by “AI” you mean freemium platforms making api calls to OpenAI with a markup, I would say most of them. If it’s easy, 100 people are already doing it.

Any idea where you are basically just a wrapper over some other other company's API.