[dr__mario]

Not sure if I'm missing something but if the authors claim:

1. That chatbots don't understand what they are producing -> a search engine doesn't either.

2. The benefit of search is that you engage in sense-making -> you actually need to do that with a chatbot too.

3. You would want access to the sources -> that's already fixed for today's chatbots (see perplexity.ai, for example, which offers links next to its claims).

4. We may trust chatbots more easily because of their language: we already have that problem with search results.

I understand the idea that there will not be an ever-knowing AI and we will probably don't even want one. But what we have today seems an improvement over a search engine (not necessarily a replacement).

[elurg]

Providing sources is the most important feature missing in chatgpt and perplexity.ai does indeed attempt to solve it. The other problem is that chatgpt is often factually incorrect and gives no hint of uncertainty.

I've been using perplexity.ai recently and often times the results are more helpful than google and it tends to spew less opaque bullshit than chatgpt.