On top of that, it's one thing to write the code, whereas it's another to actually run that code with maximal reliability and minimal downtime. I'm sure LLMs can churn out Terraform all day long, but can they troubleshoot when something goes wrong (as is often the case)?
Sounds like a fun experiment, let AI completely control an infrastructure, from application layer to load balancing and databases.
I bet it would burn a lot of money very fast and not just on tokens.