I've come to mostly use ai to bounce ideas off of. Even that has gotten less useful these last few months for some reason. Now it either wants to do the work for me or just spit out a complete agreement without being any bit critical.
It's known that OpenAI tweaked ChatGPT output so it's very agreeable and flattering no matter what the input is. Which turns out to be a problem because even the most schizophrenic paranoid rant will get an enthusiastic response praising how the user isn't a sheep and doesn't blindly conform to societal norms etc.
And why did they make this change? Because it makes users spend more time on the platform. ChatGPT wasn't just one of the fastest-growing web services ever, it's now also speedrunning enshittification.