Earlier this year, AI was like working with a recent intelligent technical college graduate who was answering questions and making good suggestions I didn’t think of. Recently, it is like I have an HR intern helping me. The AI assistant can’t answer science related questions, doesn’t suggest anything useful, asks chatty questions about what I think despite my instructions, formats wrong despite instructions, and is constantly telling me why I can’t search for or do something that is not even remotely an issue . . . Even practicing my Spanish in terms of lessons plans, not just chatting, is painful now.
What less obvious models are you all using today to avoid this problem on your aggregators?
[link] [comments]