All my AI startups are powered by @FAL so I invested in them They're one of the nicest people to work with, extremely fast inference times but also extremely fast support The founders are Turkish and now I have a special thing for 🇹🇷 Turkey and wanna visit Istanbul, hard working people that don't tolerate bullshit, I like it The business case for FAL seems real, I tried setting up my own GPU server on @LambdaAPI, it's fun and I got quite far installing Claude Code and letting it do everything But you still get stuck pretty fast, it's a lot of work to manage the layer between GPU and actually getting an AI model to output something fast while being able to scale up on demand (remember other startups with their "Queued" problems when you try run a job) So FAL has its role, it backs a lot of the AI apps you use because the founders want to focus on building useful apps, not mess around with GPU servers