One of the things that makes #LLM #Chatbots seem like they can carry on a conversation is that they adjust their state according to the conversation as it evolves, and respond in light of previous comments from both participants.

This may be good for a conversation, but naively implemented, it's quite a bad thing for a search tool / knowledge engine.

Here's an example. Here one answer Bard gives when you ask it what I think of the InfoMap algorithm that I co-developed with Martin Rosvall.

Set aside the quotes that it incorrectly attributes to me in a blog post I didn't write.

What is far more interesting is that here is polar opposite answer to exactly the same query.

FWIW, I never disavowed InfoMap and thinks it works quite well, though I'm perhaps not as boastful as it suggested in the previous answer.

@ct_bergstrom Is this GPT-4?