[lanyard-textile]

I've been tempted for a long time.

I don't think I would need VC to get off the ground.

I keep coming back to the gigantic headache of content moderation, and it gives me pause not to do it. There are some truly terrible people who will try to tear the platform apart.

[hx8]

I think automatic moderation is one of those golden use cases for LLMs. You can use cheaper inference models, and maybe some clever sampling techniques to limit the token expense.

Thinking out loud, I'd be surprised if this isn't a startup already.

[lanyard-textile]

I wonder if you break TOS by sending unlawful content that way... :) Would have to be local model I'd imagine.