[cfcf14]

Yeah - more or less.

I still use it sometimes for trivial stuff like giving me recipe or travel inspiration (using the web search API), but I haven't been using it for any sort of algorithms/coding stuff.

It's useful for tasks which have a high tolerance for not being completely correct. Which is definitely a subset of all tasks that interest me, but it's a smaller subset that I originally thought it would be. It's just really hard to find out where the models are wrong when it's a complex question. If it wasn't, then I wouldn't need the tool, I guess.