In my view, this is an example of a problem with AI ethicists: they tend to naively overestimate the statu quo. In this particular case, the premise seems to be that people obtain reliable information from traditional search engines, hence chatbots cannot replace them because they are unreliable.
The truth: many uses of a search engine aren't even things where reliability matters much (what's the weather tomorrow? what's artist X's latest song?). For those where it does matter, results are unreliable as well, because the web is full of all kinds of crap and any attempt at sorting the wheat from the chaff failed many years ago. And sure, users can try to assess the reliability of the sources. Good luck with that (not you specifically, well-educated and tech-savvy HN reader, but at a population level). All those extremist propaganda sites that are climate denialists, antivaxxers, etc. have readers that think they are perfectly reliable.
Of course there are situations where checking the sources works (e.g. a scientist working on a literature review)... which, of course, are the situations where those people aren't going to trust ChatGPT anyway.
In summary, I think this kind of criticism widely misses the mark. The problem with this and other current issues is the corporate interests feeding us all kinds of crap, not whether the way of feeding it is more convenient or less.