>1. This is a 2022 era picture that LLMs just suck up what's on the Internet and regurgitate it. It hasn't been true for a long time.

When I ask ChatGPT certain questions, it very clearly shows me the sources it's searching through in the form of favicons, and they're always the favicons of sites that are in the first 5-10 results for a Google search query that would fit what I've asked the LLM. It will then cite those websites as it's source, with a direct link to the page that also shows up in an equivalent Google search. It does that daily.

▲

baliex 7 hours ago | parent | next [-]

It's possible that the favicons it shows and the web pages that are actually retrieved are not the same

	▲	jdlshore 7 hours ago \| parent [-]
		Why do you believe that? The favicons seem like they’re generated by the UI, not the LLM. On the other hand, I recently asked ChatGPT for some information about a group of people, and the headshots it put with each summary were very clearly not the people it was describing. So hallucinations do still occur even on the latest models, it just seems unlikely that the favicons would be LLM-generated.

▲

pixl97 7 hours ago | parent | prev [-]

I think they are talking about training not run time search.