- I post/repost this information every time I see it because every time I hear a mostly offline person talking about it, it’s in the same breath as Google and boy are they not the same thing.
- Chatbots — LLMs — do not know facts and are not designed to be able to accurately answer factual questions. They are designed to find and mimic patterns of words, probabilistically. When they’re “right” it’s because correct things are often written down, so those patterns are frequent. That’s all.
