You’re getting downvoted because you couldn’t even make it through one sentence without dismissing valid concerns. You simply assert that the results are better without showing awareness of the argument, which reveals your accusation of ideological bias to be rather blatant projection when you’re not even demonstrating awareness of the problems, much less the expertise needed to dismiss them. The accuracy issues are real and significant–you should especially learn about the research showing the problem when something wrong or incomplete is presented authoritatively by a trusted source like Google rather than some random blogger–but that’s not the only problem: Google is effectively parasitizing the open web which made them rich by no longer sending visitors to the sites which provide original content. That might be profitable for them but it’s worse for everyone else — even as a Google shareholder I think this shouldn’t be allowed.
I’m saying that when you start by dismissing a large group of people with a range of views as hysterical it’s pretty clear that you’re not here for any intellect reasons but rather just to defend a technology which you’ve incorporated into your self-identity.
“The accuracy issues are real” my main point was that ChatGPT is more accurate than Google or kagi. If you can’t even believe this or you need sources, there’s no debate. You are ignorant of the strengths of LLMs.
That’s not just wrong but a category error[1] and it also misses the other arguments. The fact that you think wanting sources is a problem is a rather perfect demonstration that you aren’t approaching this carefully, though.
Ironically, if you ask an LLM this question it gives a much better answer than you have so far, although both of the ones I used still miss the larger impact on the web.
1. A search result’s accuracy is attributed to the source, whereas an LLM’s summary is attributed to the LLM—especially in the cases where it “cites” sources which don’t make the claims it emitted.
> 1. A search result’s accuracy is attributed to the source, whereas an LLM’s summary is attributed to the LLM—especially in the cases where it “cites” sources which don’t make the claims it emitted.
This makes no sense. Don’t ask the llm for summary. Ask it for the links directly. In what way are they different? ChatGPT is a superset of a search engine.
