LLMs like ChatGPT reward detailed prompts with better responses, while Google search tends to degrade with longer queries.
This contrast makes it harder for people used to Google to maximize LLM potential, as effective prompting requires a different approach than traditional keyword-based search.
This contrast makes it harder for people used to Google to maximize LLM potential, as effective prompting requires a different approach than traditional keyword-based search.
Comments
I think it's part (not all) of why Google has gotten worse for me lately, it's optimizing for the way younger people use it, and that's probably a better fit for LLM responses too.
90% of the time, if you reply to a response with "Really?", the follow-on response will start "Apologies for the incorrect information in my last reply..."