Replying to an earlier post

“Don’t tell me what isn’t so,” has to be something I say on an hourly basis when I use AI. If you ever correct anything, it just writes itself little notes like doing something dumb would be the obvious behavior otherwise.

“This service does not use JPA, it uses JDBC, so don’t add Hibernate to the dependencies.”

Motherfucker, what? Four words: “this service uses JDBC.” I swear it’s a gimmick to make AI use more tokens.

Replying to an earlier post

Using AI to automate tasks that could be automated with a script is awful. And if the endpoints are there for AI to trigger actions, then a simple script could use those same endpoints to do the same thing.

Using AI to help write the script? (Strong emphasis on “help”) Ok, maybe in some scenarios.

But just constantly running AI to do shit is like firing up your big diesel pickup to go down the block to visit your neighbors, except in this case the diesel truck can’t even be trusted to reliably take you to your neighbors every time you want to go there. There’s always the chance it’s going to decide to go somewhere else.