The issue is, people think that connecting an LLM to the internet = unlimited information. In reality, it = an LLM treating a webpage as another sources of information. It is no better or worse than literally copying and pasting the information into the text box. If it goes beyond the token limit, you are going to get swiss cheese responses.
Bing is okay, ChatGPT 4 with browe tool is okay and Bard is pretty good, but tends to not use its browse tool enough, and hallucinates mightily.
Bing is okay, ChatGPT 4 with browe tool is okay and Bard is pretty good, but tends to not use its browse tool enough, and hallucinates mightily.